DAILY CRUDE OIL PRICE FORECASTING MODEL USING ARIMA, GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTIC AND SUPPORT VECTOR MACHINES

Size: px
Start display at page:

Download "DAILY CRUDE OIL PRICE FORECASTING MODEL USING ARIMA, GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTIC AND SUPPORT VECTOR MACHINES"

Transcription

1 Amercan Journal of Appled Scences (3): 45-43, 04 ISS: Scence Publcaton do:0.3844/ajassp Publshed Onlne (3) 04 ( DAILY CRUDE OIL PRICE FORECASTIG MODEL USIG ARIMA, GEERALIZED AUTOREGRESSIVE CODITIOAL HETEROSCEDASTIC AD SUPPORT VECTOR MACHIES Rana Abdullah Ahmed and An Bn Shabr, Department of Mathematcal Scences, Unverst Teknolog Malaysa, Skuda, Johor, 830, Malaysa Department of Mathematcs, College of Basc Educaton, Unversty of Mousl, Mousl, Iraq Receved ; Revsed 03--9; Accepted ABSTRACT Crude ol prce forecastng s ganng ncreased nterest globally. Ths nterest s due manly to the economc value attached to the product. For ths reason, new forecastng methods are proposed n the lterature. Ths paper proposes a novel technque for forecastng crude ol prce based on Support Vector Machnes (SVM). The study adopts the data on crude ol prce of West Texas Intermedate (WTI) for ts expermental purposes. Ths s because many studes have prevously used ths same data and t wll afford a common bass for assessment. To evaluate the performance of the model, the study employs two measures, RMSE and MAE. These are used to compare the performance of the proposed technque and that of ARIMA and GARCH methods for the most effcent n crude ol prce forecastng. The results reveal that the proposed method outperforms the other two n terms of forecast accuracy whle t acheved a forecast error of that of ARIMA and GARCH were and.034 respectvely judgng by ther RMSE. Keywords: Support Vector Machne, Forecastng, GARCH, Ol Prce and ARIMA. ITRODUCTIO Forecastng crude ol prces s mportant as t affects other key sectors of the economy ncludng the stock market. One of the mportant areas n economc research s forecastng the trend of prce change of nternatonal crude ol. It s also a ponter n numerous ndustres for quck management nterventon due to the recent extreme fluctuatons n the prce of nternatonal crude ol. Ths makes t crucal to develop relable models that would assst adequately n forecastng the fluctuaton of nternatonal crude ol prce. Ths s amed at facltatng the partes nvolved n takng approprate acton to avod assocated rsk. The ncrease n prce of nternatonal crude ol and ts daly changes does not only affect the fnancal markets and economes, but t also affects ndvduals too. Ths s because of prce ncrease of crude ol mpacts greatly on the prce of petrol whch has ts country and by extenson the gross domestc product (GDP). GDP has been defned by (Chrystal & Lpsey) as the total goods and servces produced n a country wthn a gven year. The aforementoned reasons makes the predcton of crude ol prces a very mperatve task to decrease the mpact of prce fluctuatons and assst polcy makers and ndvduals to take nformed decsons that would help n copng wth prce fluctuatons arsng from the energy markets. However, because of the mentoned reasons predctng crude ol s not a smple task. These have all made the predcton of the crude ol prce a wdely researched nto area n the energy market. The models found n the lterature on crude ol prce forecastng nclude the popular Box-Jenkns method as n (Lu, 99; Chnn et al., 005; Agnolucc, 009). Othermodels explored nclude GARCH-type models as n (Ahmed and Shabr, 03; Hou and Saudy, 0; Sadorsky, 006). In ths study, we attempt to extend the models used n the study of crude ol prce to attendant effect on goods and servces produced n the Correspondng Author: An Bn Shabrl, Department of Mathematcal Scences, Unverst, Teknolog Malaysa, Skuda, Johor, 830, Malaysa 45

2 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 the realm of the artfcal ntellgence partcularly fttng a Support Vector Machne (SVM) to the forecast such data of hgh volatlty. Secton that follows ths ntroducton dscusses revews of related works, Secton 3 dscusses the methodology n whch we concentrate on the mathematcal formulatons of the three methods n ths study and Secton 4 dscusses the results of the fndngs, whle Secton 5 gves the concluson of the paper. Secton 6 s devoted to acknowledgement n whch we apprecated the assstance receved from corporate bodes and ndvduals towards makng ths research come to lght.. REVIEW OF RELATED LITERATURE Lu (99) employed Box-Jenkns technque to study the dynamc relatonshps between US crude ol prces, gasolne prces and the stock of gasolne wth transferrng functon models US, whle Kumar (99) used tme seres models to nvestgate and compare the forecast accuracy of future prces of crude ol. The study ft an ARMA (,) model as the best ft model and compared wth future crude ol prces wth. The merts of ARIMA models are twofold (Wang et al., 005). Intally, ARIMA models are a set of typcal lnear models whch are proposed for the lnear tme seres and captured lnear characterstcs n the tme seres. Subsequently, the theoretcal base of ARIMA models s deal. Chnn et al. (005) studed the predctve content of energy futures. They examned the relatonshp between spot and futures prces for energy commodtes. An ARIMA (,,) was used for crude ol prces forecast. Sadorsky (006) showed that the out-of-sample forecasts of a sngle equaton GARCH model are best for those of Vector Auto-regresson, state space and bvarate GARCH models, are more superor n forecastng the futures prces of petroleum. Agnolucc (009) utlzed dverse knds of GARCH models and mentoned nstablty models to predct daly WTI future prce nstablty, but the emprcal results exposed that ther performances were ncompatble wth regard to dverse measures and statstcal tests. Marzo and Zagagla (00) appled numerous GARCH models to predct the nstablty of daly futures prces of crude ol traded on YMEX. The authors concluded they have not found a contnuously greater model based on dverse statstcal tests such as DM test, drecton accuracy test and performance 46 measures as Success Rato, Heteroscedastcty adjusted MSE, MAE and MSE. Hou and Saudy (0) an alternatve approach nvolvng nonparametrc method to model and forecast ol prce return volatlty, the results demonstrate that the out-of-sample nstablty predcton of the nonparametrc GARCH model defers greater performance qualfed for a broad class of parametrc GARCH models. Ahmed and Shabr (03) appled ftted GARCH model to crude ol spot prces. Ths was done n order to llustrate the advantages of nonlnear models. In the study the authors ft three GARCH models namely; GARCH-, GARCH-t and GARCH G to crude ol spot prces. The results revealed that GARCH- model s the best model for forecastng for Brent whle GARCH-G model s the best for forecastng of WTI crude ol spot prces. Morana (00) showed how the ol prce allocaton can be predcted by usng the GARCH propertes of ol prce changes over short-term horzons. He used a sem-parametrc approach to ol prce forecastng and t was based on bootstrap approach. Accordng to Marmoutou et al. (009), the GARCH (,) -model may provde equally good results when compared to a combned GARCH and Extreme Value Theory (GARCH-EVT). Sadorsky (999) showed that ol prce nstablty alarms have dssymmetrcal effects on the fnancal system. The fluctuatons n ol prces nfluence fnancal actvty, but modfcaton n fnancal actvty has lttle mpact on ol prces. Most recently, Support Vector Machne (SVM) a novel neural network algorthm, was developed by Vapnk (995) has ganed sgnfcant nroad n the feld of forecastng. Amongst the unque propertes of SVM s that t s opposed to the over-fttng dffculty and can draw model nonlnear relatons n a stable and effcent way. Addtonally, SVM s nstructed as a curved optmzaton problem resultng n the global explanaton that n many cases defers exclusve explanatons. Intally, SVMs have been expanded for categorzaton tasks (Burges, 998). SVMs have been expanded to resolve tme seres predcton and nonlnear regresson problems, wth the ntroducton of Vapnk s ε-nsenstve loss functon and they show excellent performance (Huang et al., 005; Muller et al., 997). Derved from ths standard, SVMs wll ultmately produce better smplfcaton performance n comparson wth other neural networks. Due to such

3 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 benefts, SVM method has been used n the area of economc tme seres forecastng (Tay and Cao, 00; 00; Km, 003; Huang et al., 005). Whereas, n comparng wth customary neural networks, the outstandng applcaton of SVMs s derved from the state that the modeled data should have defnte consstency. Accordngly, for the tme seres data wth changng dynamcs, a partcular SVM model could not acheve well n capturng such dynamc and unstructured nput-output relatonshp ntrnsc n the economc data. Khashman and wulu (0a) showed an ntellgent system that forecasts the crude ol prce. Ths ntellgent system s derved from SVM, the outcomes ganed were very hopeful as t establshed that SVM could be utlzed wth a hgh accuracy n forecastng the prce of crude ol. Xao-Ln and Ha-We (0) adopt three basc kernel functons of SVM to buld the predcton model of the crude ol prce, t used a partcle swarm algorthm to optmze the parameters. The result show the predcton model whose parameters have been optmzed by a genetc algorthm. Khashman and wulu (0b) nvestgated and compared the applyng of a back propagaton neural network and an SVM to the task of forecastng ol prces and the outcomes propose the neural networks can be competently appled to forecast future ol prces wth mnmal computatonal expendture. 3. THE METHODOLOGY In ths Secton, the paper dscusses the three technques that feature promnently n ths study. These are ARIMA, GARCH and SVM. Emphass s lad on how the proposed SVM technque would be mplemented n crude ol prce forecastng. 3.. ARIMA Modelng Box and Jenkns (976) ntroduced the ARIMA model and ever snce then the method has turned out to be one of the most famous approaches to predctng. The future value of a varable n an ARIMA model s presumed to be a lnear combnaton of past errors and past values, stated as follows: y = θ + φ y + φ y φ y t 0 t t p t p +ε θ ε θ ε... θ ε t t t q t q () 47 where, y t s the actual value and φ and θ j are the coeffcents, p and q are ntegers that are frequently submtted to as autoregressve, ε t s the random error at tme t and movng average polynomals, n that order. Fundamentally, ths method has three stages: Model classfcaton, parameter evaluaton and dagnostc examnaton. For nstance, the ARIMA (,0,) model can be characterzed as follows Equaton (): yt = θ 0 + φ yt + εt θε t () Equaton () demands some sgnfcant partcular cases of the ARIMA famly of models. If q = 0, then () becomes an AR model of order p. When p = 0, the model decreases to a MA model of order q. One essental task of the ARIMA model buldng s to conclude the sutable model order (p, q). Accordng the prevous work, Box and Jenkns (976) developed a practcal approach to buldng ARIMA models, whch has the fundamental mpact on the tme seres analyss and forecastng applcatons. Box and Jenkns recommended to apply the Partal Autocorrelaton Functon (PACF) and the Autocorrelaton Functon (ACF) of the sample data as the fundamental tools to recognze the order of the ARIMA model. In the classfcaton step, data transformaton s frequently necessary to make the tme seres statonary. Statonarty s an essental stage n creatng an ARMA model appled for predctng. A statonary tme seres s descrbed by statstcal characterstcs for nstance the mean and the autocorrelaton structure beng stable ultmately. Whle the expermental tme seres shows heteroscedastcty and trend, power transformaton and dfferencng are used to the data to elmnate the trend and to become constant the varance before can be ftted an ARIMA model. 3.. GARCH Modelng The ARIMA (p, d, q) model cannot capture the heteroscedastc outcomes of a tme seres procedure, characterstcally examned n the shape of hgh kurtoss, or gatherng of volatltes and the nfluence effect. Engle (98) ntated the Autoregressve Condtonal Heteroscedastc (ARCH) model, afterward Bollerslev (986) generalzed t thus the name

4 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 Generalzed Autoregressve Condtonal Heteroscedastc model (GARCH). The term condtonal mples the level of assocaton on the past sequence of observatons and the autoregressve descrbes the feedback mechansm that ncorporates past observatons nto the present (Laux et al., 0). The varance equaton of the GARCH (p, q) model can be expressed as Equaton (3 and 4): ε = Z σ t t t Z ~ Ψ(0,) p p t t t j = j= σ = ω + α ε + β σ = ω + α(b) ε + β(b) σ t t j (3) (4) where, Ψ t (0, ) s the lkelhood densty functon of the resduals or nnovatons wth unt and zero mean varance. Intentonally, τ are extra dstrbutonal parameters to explan the shape and the skew of the dstrbuton. The GARCH model can be reduced to the ARCH model f all the coeffcentsβ are zero. Smlar to ARMA models a GARCH requrement frequently gudes to a more economcal representaton of the chronologcal dependences and therefore presents a comparable addtonal flexblty over the lnear ARCH model when parameterzng the condtonal varance. Bollerslev (986) has demonstrated that the GARCH (p, q) procedure s wde-sense statonary f the followng condtons hold: E(ε t ) = 0 ω var( ε t ) = ( α() β()) cov( εt, εs ),t sf andonlyf () + () < The smple GARCH (, ) model has been establshed to offer a good demonstraton of an extensve dversty of volatlty procedures n most applcatons, (Bollerslev et al., 99) Support Vector Machnes Vapnk (995) proposed the Support Vector Machnes (SVMs). Accordng to the Structured Rsk Mnmzaton (SRM) prncple, SVMs look for reducng an upper bound of the generalzaton error rather than the emprcal error as n other neural 48 networks. Furthermore, the SVMs models create the revert functon by concernng a set of hgh dmensonal lnear functons. The SVM regresson functon s formulated as follows Equaton (5): y(x) = w φ (x) + b (5) where, Φ(x) s named the feature, whch s nonlnear planed from the nput space x. The coeffcents w and b are evaluated by mnmzng Equaton (6 and 7): R(C) = C L ε (d, y ) + w (6) = d y ε d y ε L ε(d, y ) = (7) 0 others where, both C and ε are prescrbed parameters. The frst term L s (d, y ) s named the ε-ntensve loss functon. The d s the actual stock prce durng the th perod. Ths functon shows that errors below are not penalzed. Also the term ( C( ) L (d, y ) measures = z the emprcal error. The next term, w s the flatness of the functon. C assesses the trade-off between the flatness of the model and the emprcal rsk. ξ and ξ were ntroduced as the postve slack varables, whch sgnfy the dstance from the actual values to the correspondng boundary values of ε-tube. Equaton (4) s converted to the followng constraned formaton: Mnmze: ( ) T R(w, ξ, ξ ) = ww + C ( ξ + ξ ) = Subjected to Equaton (9 to ): (8) w φ (x ) + b d ε + ξ (9) d w φ(x ) b ε + ξ (0) where ξ ξ 0, =,,..., () Fnally, ntroducng Lagrange multplers and maxmzng the dual functon of Equaton (8) we have:

5 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 = = R( α α ) = d ( α α ) ε ( α α ) ( α α j) ( α j α j)k(x,x j ) = j= Wth the constrants Equaton (3 to 5): () ( α α ) = 0 (3) = 0 α C (4) 0 α C =,,..., (5) In Equaton (), α and α are called Lagrangan multplers. They satsfy the equaltes Equaton (6): scenaro, testng and valdatng data requre data collecton. Although, the data collected from a varety of sources must be chosen along wth the equvalent norms. Sample preprocessng s the second phase that comprses of two steps: Frst step nvolves data normalzaton and second step s data dvson. In the process of developng any model, famlarty wth the accessble data s one of the greatest sgnfcance. SVM s no excepton to ths rule, as well; data normalzaton n can nfluence model performance sgnfcantly. Subsequently, data collecton should be dvded nto two sub-sets: Frst n-sample data and second out-of-sample data whch are appled for model development and model evaluaton n that order. SVM tranng and learnng s the thrd phase. Ths phrase comprses three major tasks: Determnaton of SVM archtecture, sample tranng and sample valdaton, whch s the center procedure of the SVM model. α α = 0 l α α + = f (x,a,a) ( )K(x,x ) b (6) Here, K(x, x ) s named the kernel functon. The amount of the kernel s equvalent to the nner product of two vectors x and x j n the feature space φ(x ) and φ(x j ), such that K(x, x ) = φ(x )φ(x j ). Any functon that fulfllng Mercer s condton Vapnk (995) can be appled as the kernel functon. The Gaussan kernel functon: ( ) K(x,x ) = exp x x / σ j j Is specfc n ths study. The SVMs were used to evaluate the nonlnear behavor of the predctng data set because Gaussan kernels am to present good performance under common effcency assumptons Proposed SVM Implementaton The flowchart of the proposed SVM technque s shown n Fg.. Ths gves a vvd llustraton of the procedure for expandng an SVM for tme seres predctng. The flowchart n Fg. can be splt nto four phases. The frst phase s data samplng. To expand an SVM model for a predctng tranng, Fg.. A flow chart of SVM-based forecastng system 49

6 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 SVM-based crude ol prce forecastng nvolves four steps: Data samplng. For ths research varous data can be collected, for example YMEX, WTI. Data collected can be classfed nto dverse tme scales: Daly, weekly and monthly. For daly data, there are a varety of mssng ponts and nconsstences for the marketplace has been blocked or stopped because of unexpected events or weekends. Consequently, weekly data and monthly data should be approved as alternatves Data preprocessng. It may requre to be transformed the collected ol prce data nto a defnte sutable range for network learnng va logarthm transformaton, varaton or other methods. After that the data should be splt nto out-of-sample data and n-sample data Tranng and learnng. In ths step the tranng results determne the SVM archtecture and parameters. There are no norms n choosng the parameters other than a tral-and-error bass. In ths study, the RBF kernel s appled because the RBF kernel tends to provde good performance under common softness assumptons As a result, t s partcularly constructve f no extra nformaton of the data s accessble. In concluson, an acceptable SVM-based model for ol prce predctng s attaned. Future prce forecastng Selectng correspondng SVM parameters s the modelng: Kernel functon and penalty factor c, whch nfluence sgnfcantly on the predctng outcomes. Statstcal software was used to create evaluaton among sgmod kernel functon, radal bass functon, kernel functon and polynomal kernel functon. In concluson, the radal bass functon was selected for the hgh predcton accurateness and concurrently through many trals of the parameter computaton Data For ths study, the West Texas Intermedate (WTI) crude ol spot prce was adopted for expermental purposes. The reason of choosng the ol prce sgns s that, the crude ol prces are the most well-known standard prces, whch are extensvely appled at the 430 foundaton of many crude ol prce codes. The crude ol prce data utlzed n ths study are daly data and are generously avalable from the energy nformaton admnstraton (EIA).The data covers the perod January, 986 to September 30, 006, thereby gvng a total of 537 observatons. The data s presented n Fg.. A dfference n unt can result n a dfference n data magntude, whch tends to affect predcton accuracy n the long run. The normalzaton processng can resolve ths ssue. In ths study, the data was normalzed to a scalable range of [0,] n the tranng set and predcton set, usng the normalzaton equaton: ( ) ( ) X = X X / X X n mn max mn The normalzed data s shown n Fg Evaluaton of Volatlty Forecasts Ths study adopted two very popular measures for evaluatng the forecast accuracy of the seres and these are: Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). These measures are evaluated by assessng ther returns. The one wth the lowest error measure s judged the best. These measures are defned as follows. Mean Absolute Error (MAE) s gven by: MAE = X X p ˆ t = ( t ) Fg.. The tme seres for WTI daly t

7 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 Fg. 3. The normalzed data for WTI Table. The evaluaton of forecastng results for WTI crude ol prce Methodology RMSE MAE ARIMA GARCH SVM and Root Mean Squared Error (RMSE) s gven by: (( ) ) / ˆ t t k RMSA = x x p t = Where: X t : The return of the horzon before the current tme t X : The average return ˆp t : Is the forecast value of the condtonal varance over n steps ahead horzon of the current tme t 3.7. Results and Analyss The results are shown n Table. From Table t can be seen that the proposed method SVM outperforms GARCH and ARIMA technques. From the pont of vew of the RMSE t returned a forecast error of followed by ARIMA wth a forecast error of and then GARCH wth.034. For the MAE SVM stll post the best result wth forecast accuracy of ; ARIMA and GARCH COCLUSIO In ths study a novel approach based on artfcal ntellgence for crude ol prce modelng s proposed. The proposed technque forecast accuracy performance was evaluated usng two measures of error RMSE and MAE and compare wth some other well-known technques n crude ol spot prce forecastng lke ARIMA and GARCH. The results revewed that the proposed SVM method outperforms the others. The study therefore recommends that the proposed SVM method be employed n future for crude ol prce forecastng. 5. REFERECES Agnolucc, P., 009. Volatlty n crude ol futures: A comparson of the predctve ablty of GARCH and mpled volatlty models. Energy Econ., 3: DOI: 0.06/j.eneco Ahmed, R.A. and A.B. Shabr, 03. Fttng GARCH models to crude ol spot prce data. Lfe Sc. J., 0: Bollerslev, T., 986. Generalzed autoregressve condtonal heteroskedastcty. J. Econometr., 3: DOI: 0.06/ (86) Bollerslev, T., R.Y. Chou and K.F. Kroner, 99. ARCH modelng n fnance : A revew of the theory and emprcal evdence. J. Econ., 5: DOI: 0.06/ (9)90064-X

8 Rana Abdullah Ahmed and An Bn Shabr / Amercan Journal of Appled Scences (3): 45-43, 04 Box, G.E.P. and G. Jenkns, 976. Tme Seres Analyss: Forecastng and Control. st Edn., Holden-Day, San Francsco, ISB-0: , pp: 575. Burges, C.J.C., 998. A tutoral on support vector machnes for pattern recognton. Data Mnng Knowl. Dscovery, : -67. DOI: 0.03/A: Chnn, M.D., M.R. LeBlanc and O. Cobon, 005. The Predctve Content of Energy Futures: An Update on Petroleum, atural Gas, Heatng Ol and Gasolne. st Edn., atonal Bureau of Economc Research, pp: 7. Engle, R.F., 98. Autoregressve condtonal heteroscedastcty wth estmates of the varance of unted kngdom nflaton. Econometrca, 50: Hou, A. and S. Suard, 0. A nonparametrc GARCH model of crude ol prce return volatlty. Energy Econ., 34: DOI: 0.06/j.eneco Huang, W., Y. akamora and S. Wang, 005. Forecastng stock market movement drecton wth support vector machne. Comput. Operat. Res., 3: DOI: 0.06/j.cor Khashman, A. and.i. wulu, 0a. Intellgent predcton of crude ol prce usng support vector machnes. Proceedngs of the IEEE 9th Internatonal Symposum on Appled Machne Intellgence and Informatcs, Jan. 7-9, IEEE Xplore Press, Smolence, pp: DOI: 0.09/SAMI Khashman, A. and.i. wulu, 0b. Support vector machnes versus back propagaton algorthm for ol prce predcton. Proceedngs of the 8th Internatonal Conference on Advances n eural etworks, May 9-Jun. 0, Sprnger Verlag Berln, Guln, Chna, pp: DOI: 0.007/ _60 Km, K.J., 003. Fnancal tme seres forecastng usng support vector machnes. eurocomputng, 55: DOI: 0.06/S095-3(03)0037- Kumar, M.S., 99. The forecastng accuracy of crude ol futures prces. Int. Monetary Fund, 39: DOI: 0.307/ Laux, P., S. Vogl, W. Qu, H.R. Knoche and H. Kunstmann, 0. Copula-based statstcal refnement of precptaton n RCM smulatons over complex terran. Hydrol. Earth Syst. Sc., 5: DOI: 0.594/hess Lu, L.M., 99. Dynamc relatonshp analyss of us gasolne and crude ol prces. J. Forecast., 0: DOI: 0.00/for Marmoutou, V., B. Raggad and A. Trabels, 009. Extreme value theory and value at rsk: Applcaton to ol market. Energy Econ., 3: DOI: 0.06/j.eneco Marzo, M. and P. Zagagla, 00. Volatlty forecastng for crude ol futures. Appled Econ. Lett., 7: DOI: 0.080/ Morana, C., 00. A semparametrc approach to shortterm ol prce forecastng. Energy Econ., 3: DOI: 0.06/S (00)00075-X Muller, K.R., J.A. Smola and B. Scholkopf, 997. Predctng tme seres wth support vector machnes. Proceedngs of the Internatonal Conference on Artfcal eural etworks, Oct. 8-0, Swtzerland, pp: DOI: 0.007/BFb00083 Sadorsky, P., 999. Ol prce shocks and stock market actvty. Energy Econ., : DOI: 0.06/S (99)0000- Sadorsky, P., 006. Modelng and forecastng petroleum futures volatlty. Energy Econ., 8: DOI: 0.06/j.eneco Tay, E.H. and L.J. Cao, 00. Applcaton of support vector machnes n fnancal tme seres forecastng. Omega, 9: DOI: 0.06/S (0) Tay, F.E. and L.J. Cao, 00. Modfed support vector machnes n fnancal tme seres forecastng. eurocomputng, 48: DOI: 0.06/S095-3(0) Vapnk, V.., 995. The ature of Statstcal Learnng Theory. st Edn., Sprnger, ew York, ISB-0: , pp: 34. Wang, S.Y., L.A. Yu and K.K. La, 005. Crude ol prce forecastng wth TEI@I methodology. J. Syst. Sc. Complexty 8: Xao-Ln, Z. and W. Ha-we, 0. Crude ol prces predctve model based on support vector machne and partcle swarm optmzaton. Proceedngs of the Internatonal Conference on Software Engneerng, Knowledge Engneerng and Informaton Engneerng, (SEKEIE ), pp: DOI: 0.007/ _89

Forecasting the Direction and Strength of Stock Market Movement

Forecasting the Direction and Strength of Stock Market Movement Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems

More information

A study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns

A study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns A study on the ablty of Support Vector Regresson and Neural Networks to Forecast Basc Tme Seres Patterns Sven F. Crone, Jose Guajardo 2, and Rchard Weber 2 Lancaster Unversty, Department of Management

More information

IMPACT ANALYSIS OF A CELLULAR PHONE

IMPACT ANALYSIS OF A CELLULAR PHONE 4 th ASA & μeta Internatonal Conference IMPACT AALYSIS OF A CELLULAR PHOE We Lu, 2 Hongy L Bejng FEAonlne Engneerng Co.,Ltd. Bejng, Chna ABSTRACT Drop test smulaton plays an mportant role n nvestgatng

More information

Causal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting

Causal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting Causal, Explanatory Forecastng Assumes cause-and-effect relatonshp between system nputs and ts output Forecastng wth Regresson Analyss Rchard S. Barr Inputs System Cause + Effect Relatonshp The job of

More information

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange

More information

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services An Evaluaton of the Extended Logstc, Smple Logstc, and Gompertz Models for Forecastng Short Lfecycle Products and Servces Charles V. Trappey a,1, Hsn-yng Wu b a Professor (Management Scence), Natonal Chao

More information

Statistical Methods to Develop Rating Models

Statistical Methods to Develop Rating Models Statstcal Methods to Develop Ratng Models [Evelyn Hayden and Danel Porath, Österrechsche Natonalbank and Unversty of Appled Scences at Manz] Source: The Basel II Rsk Parameters Estmaton, Valdaton, and

More information

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Max Wellng Department of Computer Scence Unversty of Toronto 10 Kng s College Road Toronto, M5S 3G5 Canada wellng@cs.toronto.edu Abstract Ths s a note to explan support vector machnes.

More information

CS 2750 Machine Learning. Lecture 3. Density estimation. CS 2750 Machine Learning. Announcements

CS 2750 Machine Learning. Lecture 3. Density estimation. CS 2750 Machine Learning. Announcements Lecture 3 Densty estmaton Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Next lecture: Matlab tutoral Announcements Rules for attendng the class: Regstered for credt Regstered for audt (only f there

More information

Can Auto Liability Insurance Purchases Signal Risk Attitude?

Can Auto Liability Insurance Purchases Signal Risk Attitude? Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang

More information

An Interest-Oriented Network Evolution Mechanism for Online Communities

An Interest-Oriented Network Evolution Mechanism for Online Communities An Interest-Orented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne

More information

An Efficient and Simplified Model for Forecasting using SRM

An Efficient and Simplified Model for Forecasting using SRM HAFIZ MUHAMMAD SHAHZAD ASIF*, MUHAMMAD FAISAL HAYAT*, AND TAUQIR AHMAD* RECEIVED ON 15.04.013 ACCEPTED ON 09.01.014 ABSTRACT Learnng form contnuous fnancal systems play a vtal role n enterprse operatons.

More information

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network 700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School

More information

An Alternative Way to Measure Private Equity Performance

An Alternative Way to Measure Private Equity Performance An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate

More information

The Application of Fractional Brownian Motion in Option Pricing

The Application of Fractional Brownian Motion in Option Pricing Vol. 0, No. (05), pp. 73-8 http://dx.do.org/0.457/jmue.05.0..6 The Applcaton of Fractonal Brownan Moton n Opton Prcng Qng-xn Zhou School of Basc Scence,arbn Unversty of Commerce,arbn zhouqngxn98@6.com

More information

A COLLABORATIVE TRADING MODEL BY SUPPORT VECTOR REGRESSION AND TS FUZZY RULE FOR DAILY STOCK TURNING POINTS DETECTION

A COLLABORATIVE TRADING MODEL BY SUPPORT VECTOR REGRESSION AND TS FUZZY RULE FOR DAILY STOCK TURNING POINTS DETECTION A COLLABORATIVE TRADING MODEL BY SUPPORT VECTOR REGRESSION AND TS FUZZY RULE FOR DAILY STOCK TURNING POINTS DETECTION JHENG-LONG WU, PEI-CHANN CHANG, KAI-TING CHANG Department of Informaton Management,

More information

A Novel Methodology of Working Capital Management for Large. Public Constructions by Using Fuzzy S-curve Regression

A Novel Methodology of Working Capital Management for Large. Public Constructions by Using Fuzzy S-curve Regression Novel Methodology of Workng Captal Management for Large Publc Constructons by Usng Fuzzy S-curve Regresson Cheng-Wu Chen, Morrs H. L. Wang and Tng-Ya Hseh Department of Cvl Engneerng, Natonal Central Unversty,

More information

A DATA MINING APPLICATION IN A STUDENT DATABASE

A DATA MINING APPLICATION IN A STUDENT DATABASE JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul

More information

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ). REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or

More information

Recurrence. 1 Definitions and main statements

Recurrence. 1 Definitions and main statements Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.

More information

Modelling of Web Domain Visits by Radial Basis Function Neural Networks and Support Vector Machine Regression

Modelling of Web Domain Visits by Radial Basis Function Neural Networks and Support Vector Machine Regression Modellng of Web Doman Vsts by Radal Bass Functon Neural Networks and Support Vector Machne Regresson Vladmír Olej, Jana Flpová Insttute of System Engneerng and Informatcs Faculty of Economcs and Admnstraton,

More information

ECONOMICS OF PLANT ENERGY SAVINGS PROJECTS IN A CHANGING MARKET Douglas C White Emerson Process Management

ECONOMICS OF PLANT ENERGY SAVINGS PROJECTS IN A CHANGING MARKET Douglas C White Emerson Process Management ECONOMICS OF PLANT ENERGY SAVINGS PROJECTS IN A CHANGING MARKET Douglas C Whte Emerson Process Management Abstract Energy prces have exhbted sgnfcant volatlty n recent years. For example, natural gas prces

More information

Course outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy

Course outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy Fnancal Tme Seres Analyss Patrck McSharry patrck@mcsharry.net www.mcsharry.net Trnty Term 2014 Mathematcal Insttute Unversty of Oxford Course outlne 1. Data analyss, probablty, correlatons, vsualsaton

More information

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION NEURO-FUZZY INFERENE SYSTEM FOR E-OMMERE WEBSITE EVALUATION Huan Lu, School of Software, Harbn Unversty of Scence and Technology, Harbn, hna Faculty of Appled Mathematcs and omputer Scence, Belarusan State

More information

Bayesian Network Based Causal Relationship Identification and Funding Success Prediction in P2P Lending

Bayesian Network Based Causal Relationship Identification and Funding Success Prediction in P2P Lending Proceedngs of 2012 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 25 (2012) (2012) IACSIT Press, Sngapore Bayesan Network Based Causal Relatonshp Identfcaton and Fundng Success

More information

Credit Limit Optimization (CLO) for Credit Cards

Credit Limit Optimization (CLO) for Credit Cards Credt Lmt Optmzaton (CLO) for Credt Cards Vay S. Desa CSCC IX, Ednburgh September 8, 2005 Copyrght 2003, SAS Insttute Inc. All rghts reserved. SAS Propretary Agenda Background Tradtonal approaches to credt

More information

Abstract. 260 Business Intelligence Journal July IDENTIFICATION OF DEMAND THROUGH STATISTICAL DISTRIBUTION MODELING FOR IMPROVED DEMAND FORECASTING

Abstract. 260 Business Intelligence Journal July IDENTIFICATION OF DEMAND THROUGH STATISTICAL DISTRIBUTION MODELING FOR IMPROVED DEMAND FORECASTING 260 Busness Intellgence Journal July IDENTIFICATION OF DEMAND THROUGH STATISTICAL DISTRIBUTION MODELING FOR IMPROVED DEMAND FORECASTING Murphy Choy Mchelle L.F. Cheong School of Informaton Systems, Sngapore

More information

What is Candidate Sampling

What is Candidate Sampling What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble

More information

Analysis of Premium Liabilities for Australian Lines of Business

Analysis of Premium Liabilities for Australian Lines of Business Summary of Analyss of Premum Labltes for Australan Lnes of Busness Emly Tao Honours Research Paper, The Unversty of Melbourne Emly Tao Acknowledgements I am grateful to the Australan Prudental Regulaton

More information

Support Vector Machine Model for Currency Crisis Discrimination. Arindam Chaudhuri 1. Abstract

Support Vector Machine Model for Currency Crisis Discrimination. Arindam Chaudhuri 1. Abstract Support Vector Machne Model for Currency Crss Dscrmnaton Arndam Chaudhur Abstract Support Vector Machne (SVM) s powerful classfcaton technque based on the dea of structural rsk mnmzaton. Use of kernel

More information

Journal of Economics and Business

Journal of Economics and Business Journal of Economcs and Busness 64 (2012) 275 286 Contents lsts avalable at ScVerse ScenceDrect Journal of Economcs and Busness A multple adaptve wavelet recurrent neural networ model to analyze crude

More information

LSSVM-ABC Algorithm for Stock Price prediction Osman Hegazy 1, Omar S. Soliman 2 and Mustafa Abdul Salam 3

LSSVM-ABC Algorithm for Stock Price prediction Osman Hegazy 1, Omar S. Soliman 2 and Mustafa Abdul Salam 3 LSSVM-ABC Algorthm for Stock Prce predcton Osman Hegazy 1, Omar S. Solman 2 and Mustafa Abdul Salam 3 1, 2 (Faculty of Computers and Informatcs, Caro Unversty, Egypt) 3 (Hgher echnologcal Insttute (H..I),

More information

How To Calculate The Accountng Perod Of Nequalty

How To Calculate The Accountng Perod Of Nequalty Inequalty and The Accountng Perod Quentn Wodon and Shlomo Ytzha World Ban and Hebrew Unversty September Abstract Income nequalty typcally declnes wth the length of tme taen nto account for measurement.

More information

Macro Factors and Volatility of Treasury Bond Returns

Macro Factors and Volatility of Treasury Bond Returns Macro Factors and Volatlty of Treasury Bond Returns Jngzh Huang Department of Fnance Smeal Colleage of Busness Pennsylvana State Unversty Unversty Park, PA 16802, U.S.A. Le Lu School of Fnance Shangha

More information

L10: Linear discriminants analysis

L10: Linear discriminants analysis L0: Lnear dscrmnants analyss Lnear dscrmnant analyss, two classes Lnear dscrmnant analyss, C classes LDA vs. PCA Lmtatons of LDA Varants of LDA Other dmensonalty reducton methods CSCE 666 Pattern Analyss

More information

Time Delayed Independent Component Analysis for Data Quality Monitoring

Time Delayed Independent Component Analysis for Data Quality Monitoring IWSSIP 1-17th Internatonal Conference on Systems, Sgnals and Image Processng Tme Delayed Independent Component Analyss for Data Qualty Montorng José Márco Faer Sgnal Processng Laboratory, COE/Pol Federal

More information

Performance Analysis and Coding Strategy of ECOC SVMs

Performance Analysis and Coding Strategy of ECOC SVMs Internatonal Journal of Grd and Dstrbuted Computng Vol.7, No. (04), pp.67-76 http://dx.do.org/0.457/jgdc.04.7..07 Performance Analyss and Codng Strategy of ECOC SVMs Zhgang Yan, and Yuanxuan Yang, School

More information

Calculating the high frequency transmission line parameters of power cables

Calculating the high frequency transmission line parameters of power cables < ' Calculatng the hgh frequency transmsson lne parameters of power cables Authors: Dr. John Dcknson, Laboratory Servces Manager, N 0 RW E B Communcatons Mr. Peter J. Ncholson, Project Assgnment Manager,

More information

Improved SVM in Cloud Computing Information Mining

Improved SVM in Cloud Computing Information Mining Internatonal Journal of Grd Dstrbuton Computng Vol.8, No.1 (015), pp.33-40 http://dx.do.org/10.1457/jgdc.015.8.1.04 Improved n Cloud Computng Informaton Mnng Lvshuhong (ZhengDe polytechnc college JangSu

More information

Forecasting Irregularly Spaced UHF Financial Data: Realized Volatility vs UHF-GARCH Models

Forecasting Irregularly Spaced UHF Financial Data: Realized Volatility vs UHF-GARCH Models Forecastng Irregularly Spaced UHF Fnancal Data: Realzed Volatlty vs UHF-GARCH Models Franços-Érc Raccot *, LRSP Département des scences admnstratves, UQO Raymond Théoret Département Stratége des affares,

More information

Answer: A). There is a flatter IS curve in the high MPC economy. Original LM LM after increase in M. IS curve for low MPC economy

Answer: A). There is a flatter IS curve in the high MPC economy. Original LM LM after increase in M. IS curve for low MPC economy 4.02 Quz Solutons Fall 2004 Multple-Choce Questons (30/00 ponts) Please, crcle the correct answer for each of the followng 0 multple-choce questons. For each queston, only one of the answers s correct.

More information

Intra-year Cash Flow Patterns: A Simple Solution for an Unnecessary Appraisal Error

Intra-year Cash Flow Patterns: A Simple Solution for an Unnecessary Appraisal Error Intra-year Cash Flow Patterns: A Smple Soluton for an Unnecessary Apprasal Error By C. Donald Wggns (Professor of Accountng and Fnance, the Unversty of North Florda), B. Perry Woodsde (Assocate Professor

More information

On the Optimal Control of a Cascade of Hydro-Electric Power Stations

On the Optimal Control of a Cascade of Hydro-Electric Power Stations On the Optmal Control of a Cascade of Hydro-Electrc Power Statons M.C.M. Guedes a, A.F. Rbero a, G.V. Smrnov b and S. Vlela c a Department of Mathematcs, School of Scences, Unversty of Porto, Portugal;

More information

MATHEMATICAL ENGINEERING TECHNICAL REPORTS. Sequential Optimizing Investing Strategy with Neural Networks

MATHEMATICAL ENGINEERING TECHNICAL REPORTS. Sequential Optimizing Investing Strategy with Neural Networks MATHEMATICAL ENGINEERING TECHNICAL REPORTS Sequental Optmzng Investng Strategy wth Neural Networks Ryo ADACHI and Akmch TAKEMURA METR 2010 03 February 2010 DEPARTMENT OF MATHEMATICAL INFORMATICS GRADUATE

More information

A Genetic Programming Based Stock Price Predictor together with Mean-Variance Based Sell/Buy Actions

A Genetic Programming Based Stock Price Predictor together with Mean-Variance Based Sell/Buy Actions Proceedngs of the World Congress on Engneerng 28 Vol II WCE 28, July 2-4, 28, London, U.K. A Genetc Programmng Based Stock Prce Predctor together wth Mean-Varance Based Sell/Buy Actons Ramn Rajaboun and

More information

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure

More information

Risk Model of Long-Term Production Scheduling in Open Pit Gold Mining

Risk Model of Long-Term Production Scheduling in Open Pit Gold Mining Rsk Model of Long-Term Producton Schedulng n Open Pt Gold Mnng R Halatchev 1 and P Lever 2 ABSTRACT Open pt gold mnng s an mportant sector of the Australan mnng ndustry. It uses large amounts of nvestments,

More information

The Current Employment Statistics (CES) survey,

The Current Employment Statistics (CES) survey, Busness Brths and Deaths Impact of busness brths and deaths n the payroll survey The CES probablty-based sample redesgn accounts for most busness brth employment through the mputaton of busness deaths,

More information

On-Line Fault Detection in Wind Turbine Transmission System using Adaptive Filter and Robust Statistical Features

On-Line Fault Detection in Wind Turbine Transmission System using Adaptive Filter and Robust Statistical Features On-Lne Fault Detecton n Wnd Turbne Transmsson System usng Adaptve Flter and Robust Statstcal Features Ruoyu L Remote Dagnostcs Center SKF USA Inc. 3443 N. Sam Houston Pkwy., Houston TX 77086 Emal: ruoyu.l@skf.com

More information

BERNSTEIN POLYNOMIALS

BERNSTEIN POLYNOMIALS On-Lne Geometrc Modelng Notes BERNSTEIN POLYNOMIALS Kenneth I. Joy Vsualzaton and Graphcs Research Group Department of Computer Scence Unversty of Calforna, Davs Overvew Polynomals are ncredbly useful

More information

Project Networks With Mixed-Time Constraints

Project Networks With Mixed-Time Constraints Project Networs Wth Mxed-Tme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa

More information

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(7):1884-1889 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A hybrd global optmzaton algorthm based on parallel

More information

Customer Lifetime Value Modeling and Its Use for Customer Retention Planning

Customer Lifetime Value Modeling and Its Use for Customer Retention Planning Customer Lfetme Value Modelng and Its Use for Customer Retenton Plannng Saharon Rosset Enat Neumann Ur Eck Nurt Vatnk Yzhak Idan Amdocs Ltd. 8 Hapnna St. Ra anana 43, Israel {saharonr, enatn, ureck, nurtv,

More information

How To Understand The Results Of The German Meris Cloud And Water Vapour Product

How To Understand The Results Of The German Meris Cloud And Water Vapour Product Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPP-ATBD-ClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller

More information

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12 14 The Ch-squared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed

More information

Traditional versus Online Courses, Efforts, and Learning Performance

Traditional versus Online Courses, Efforts, and Learning Performance Tradtonal versus Onlne Courses, Efforts, and Learnng Performance Kuang-Cheng Tseng, Department of Internatonal Trade, Chung-Yuan Chrstan Unversty, Tawan Shan-Yng Chu, Department of Internatonal Trade,

More information

Logistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification

Logistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification Lecture 4: More classfers and classes C4B Machne Learnng Hlary 20 A. Zsserman Logstc regresson Loss functons revsted Adaboost Loss functons revsted Optmzaton Multple class classfcaton Logstc Regresson

More information

Financial market forecasting using a two-step kernel learning method for the support vector regression

Financial market forecasting using a two-step kernel learning method for the support vector regression Ann Oper Res (2010) 174: 103 120 DOI 10.1007/s10479-008-0357-7 Fnancal market forecastng usng a two-step kernel learnng method for the support vector regresson L Wang J Zhu Publshed onlne: 28 May 2008

More information

HOUSEHOLDS DEBT BURDEN: AN ANALYSIS BASED ON MICROECONOMIC DATA*

HOUSEHOLDS DEBT BURDEN: AN ANALYSIS BASED ON MICROECONOMIC DATA* HOUSEHOLDS DEBT BURDEN: AN ANALYSIS BASED ON MICROECONOMIC DATA* Luísa Farnha** 1. INTRODUCTION The rapd growth n Portuguese households ndebtedness n the past few years ncreased the concerns that debt

More information

Different Methods of Long-Term Electric Load Demand Forecasting; A Comprehensive Review

Different Methods of Long-Term Electric Load Demand Forecasting; A Comprehensive Review Dfferent Methods of Long-Term Electrc Load Demand Forecastng; A Comprehensve Revew L. Ghods* and M. Kalantar* Abstract: Long-term demand forecastng presents the frst step n plannng and developng future

More information

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT Toshhko Oda (1), Kochro Iwaoka (2) (1), (2) Infrastructure Systems Busness Unt, Panasonc System Networks Co., Ltd. Saedo-cho

More information

Cloud-based Social Application Deployment using Local Processing and Global Distribution

Cloud-based Social Application Deployment using Local Processing and Global Distribution Cloud-based Socal Applcaton Deployment usng Local Processng and Global Dstrbuton Zh Wang *, Baochun L, Lfeng Sun *, and Shqang Yang * * Bejng Key Laboratory of Networked Multmeda Department of Computer

More information

Overview of monitoring and evaluation

Overview of monitoring and evaluation 540 Toolkt to Combat Traffckng n Persons Tool 10.1 Overvew of montorng and evaluaton Overvew Ths tool brefly descrbes both montorng and evaluaton, and the dstncton between the two. What s montorng? Montorng

More information

Efficient Project Portfolio as a tool for Enterprise Risk Management

Efficient Project Portfolio as a tool for Enterprise Risk Management Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse

More information

Financial Mathemetics

Financial Mathemetics Fnancal Mathemetcs 15 Mathematcs Grade 12 Teacher Gude Fnancal Maths Seres Overvew In ths seres we am to show how Mathematcs can be used to support personal fnancal decsons. In ths seres we jon Tebogo,

More information

IDENTIFICATION AND CORRECTION OF A COMMON ERROR IN GENERAL ANNUITY CALCULATIONS

IDENTIFICATION AND CORRECTION OF A COMMON ERROR IN GENERAL ANNUITY CALCULATIONS IDENTIFICATION AND CORRECTION OF A COMMON ERROR IN GENERAL ANNUITY CALCULATIONS Chrs Deeley* Last revsed: September 22, 200 * Chrs Deeley s a Senor Lecturer n the School of Accountng, Charles Sturt Unversty,

More information

The OC Curve of Attribute Acceptance Plans

The OC Curve of Attribute Acceptance Plans The OC Curve of Attrbute Acceptance Plans The Operatng Characterstc (OC) curve descrbes the probablty of acceptng a lot as a functon of the lot s qualty. Fgure 1 shows a typcal OC Curve. 10 8 6 4 1 3 4

More information

Selecting Best Employee of the Year Using Analytical Hierarchy Process

Selecting Best Employee of the Year Using Analytical Hierarchy Process J. Basc. Appl. Sc. Res., 5(11)72-76, 2015 2015, TextRoad Publcaton ISSN 2090-4304 Journal of Basc and Appled Scentfc Research www.textroad.com Selectng Best Employee of the Year Usng Analytcal Herarchy

More information

THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION

THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION Internatonal Journal of Electronc Busness Management, Vol. 3, No. 4, pp. 30-30 (2005) 30 THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION Yu-Mn Chang *, Yu-Cheh

More information

Study on Model of Risks Assessment of Standard Operation in Rural Power Network

Study on Model of Risks Assessment of Standard Operation in Rural Power Network Study on Model of Rsks Assessment of Standard Operaton n Rural Power Network Qngj L 1, Tao Yang 2 1 Qngj L, College of Informaton and Electrcal Engneerng, Shenyang Agrculture Unversty, Shenyang 110866,

More information

THE DISTRIBUTION OF LOAN PORTFOLIO VALUE * Oldrich Alfons Vasicek

THE DISTRIBUTION OF LOAN PORTFOLIO VALUE * Oldrich Alfons Vasicek HE DISRIBUION OF LOAN PORFOLIO VALUE * Oldrch Alfons Vascek he amount of captal necessary to support a portfolo of debt securtes depends on the probablty dstrbuton of the portfolo loss. Consder a portfolo

More information

Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets

Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets Int. J. Electronc Fnance, Vol., No., 006 49 Comparson of support-vector machnes and back propagaton neural networks n forecastng the sx major Asan stock markets Wun-Hua Chen and Jen-Yng Shh Graduate Insttute

More information

Power-of-Two Policies for Single- Warehouse Multi-Retailer Inventory Systems with Order Frequency Discounts

Power-of-Two Policies for Single- Warehouse Multi-Retailer Inventory Systems with Order Frequency Discounts Power-of-wo Polces for Sngle- Warehouse Mult-Retaler Inventory Systems wth Order Frequency Dscounts José A. Ventura Pennsylvana State Unversty (USA) Yale. Herer echnon Israel Insttute of echnology (Israel)

More information

The impact of hard discount control mechanism on the discount volatility of UK closed-end funds

The impact of hard discount control mechanism on the discount volatility of UK closed-end funds Investment Management and Fnancal Innovatons, Volume 10, Issue 3, 2013 Ahmed F. Salhn (Egypt) The mpact of hard dscount control mechansm on the dscount volatlty of UK closed-end funds Abstract The mpact

More information

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..

More information

Multiple-Period Attribution: Residuals and Compounding

Multiple-Period Attribution: Residuals and Compounding Multple-Perod Attrbuton: Resduals and Compoundng Our revewer gave these authors full marks for dealng wth an ssue that performance measurers and vendors often regard as propretary nformaton. In 1994, Dens

More information

SVM Tutorial: Classification, Regression, and Ranking

SVM Tutorial: Classification, Regression, and Ranking SVM Tutoral: Classfcaton, Regresson, and Rankng Hwanjo Yu and Sungchul Km 1 Introducton Support Vector Machnes(SVMs) have been extensvely researched n the data mnng and machne learnng communtes for the

More information

Damage detection in composite laminates using coin-tap method

Damage detection in composite laminates using coin-tap method Damage detecton n composte lamnates usng con-tap method S.J. Km Korea Aerospace Research Insttute, 45 Eoeun-Dong, Youseong-Gu, 35-333 Daejeon, Republc of Korea yaeln@kar.re.kr 45 The con-tap test has the

More information

Lecture 2: Single Layer Perceptrons Kevin Swingler

Lecture 2: Single Layer Perceptrons Kevin Swingler Lecture 2: Sngle Layer Perceptrons Kevn Sngler kms@cs.str.ac.uk Recap: McCulloch-Ptts Neuron Ths vastly smplfed model of real neurons s also knon as a Threshold Logc Unt: W 2 A Y 3 n W n. A set of synapses

More information

Fault tolerance in cloud technologies presented as a service

Fault tolerance in cloud technologies presented as a service Internatonal Scentfc Conference Computer Scence 2015 Pavel Dzhunev, PhD student Fault tolerance n cloud technologes presented as a servce INTRODUCTION Improvements n technques for vrtualzaton and performance

More information

Single and multiple stage classifiers implementing logistic discrimination

Single and multiple stage classifiers implementing logistic discrimination Sngle and multple stage classfers mplementng logstc dscrmnaton Hélo Radke Bttencourt 1 Dens Alter de Olvera Moraes 2 Vctor Haertel 2 1 Pontfíca Unversdade Católca do Ro Grande do Sul - PUCRS Av. Ipranga,

More information

Calendar Corrected Chaotic Forecast of Financial Time Series

Calendar Corrected Chaotic Forecast of Financial Time Series INTERNATIONAL JOURNAL OF BUSINESS, 11(4), 2006 ISSN: 1083 4346 Calendar Corrected Chaotc Forecast of Fnancal Tme Seres Alexandros Leonttss a and Costas Sropoulos b a Center for Research and Applcatons

More information

Pricing Model of Cloud Computing Service with Partial Multihoming

Pricing Model of Cloud Computing Service with Partial Multihoming Prcng Model of Cloud Computng Servce wth Partal Multhomng Zhang Ru 1 Tang Bng-yong 1 1.Glorous Sun School of Busness and Managment Donghua Unversty Shangha 251 Chna E-mal:ru528369@mal.dhu.edu.cn Abstract

More information

CONSTRUCTING A SALES FORECASTING MODEL BY INTEGRATING GRA AND ELM:A CASE STUDY FOR RETAIL INDUSTRY

CONSTRUCTING A SALES FORECASTING MODEL BY INTEGRATING GRA AND ELM:A CASE STUDY FOR RETAIL INDUSTRY Internatonal Journal of Electronc Busness Management, Vol. 9, o. 2, pp. 107-121 (2011) 107 COSTRUCTIG A SALES FORECASTIG MODEL BY ITEGRATIG GRA AD ELM:A CASE STUDY FOR RETAIL IDUSTRY Fe-Long Chen and Tsung-Yn

More information

A Hierarchical Anomaly Network Intrusion Detection System using Neural Network Classification

A Hierarchical Anomaly Network Intrusion Detection System using Neural Network Classification IDC IDC A Herarchcal Anomaly Network Intruson Detecton System usng Neural Network Classfcaton ZHENG ZHANG, JUN LI, C. N. MANIKOPOULOS, JAY JORGENSON and JOSE UCLES ECE Department, New Jersey Inst. of Tech.,

More information

Allocating Time and Resources in Project Management Under Uncertainty

Allocating Time and Resources in Project Management Under Uncertainty Proceedngs of the 36th Hawa Internatonal Conference on System Scences - 23 Allocatng Tme and Resources n Project Management Under Uncertanty Mark A. Turnqust School of Cvl and Envronmental Eng. Cornell

More information

Economic Interpretation of Regression. Theory and Applications

Economic Interpretation of Regression. Theory and Applications Economc Interpretaton of Regresson Theor and Applcatons Classcal and Baesan Econometrc Methods Applcaton of mathematcal statstcs to economc data for emprcal support Economc theor postulates a qualtatve

More information

Transition Matrix Models of Consumer Credit Ratings

Transition Matrix Models of Consumer Credit Ratings Transton Matrx Models of Consumer Credt Ratngs Abstract Although the corporate credt rsk lterature has many studes modellng the change n the credt rsk of corporate bonds over tme, there s far less analyss

More information

A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION. Michael E. Kuhl Radhamés A. Tolentino-Peña

A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION. Michael E. Kuhl Radhamés A. Tolentino-Peña Proceedngs of the 2008 Wnter Smulaton Conference S. J. Mason, R. R. Hll, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds. A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION

More information

Development of an intelligent system for tool wear monitoring applying neural networks

Development of an intelligent system for tool wear monitoring applying neural networks of Achevements n Materals and Manufacturng Engneerng VOLUME 14 ISSUE 1-2 January-February 2006 Development of an ntellgent system for tool wear montorng applyng neural networks A. Antć a, J. Hodolč a,

More information

"Research Note" APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES *

Research Note APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES * Iranan Journal of Scence & Technology, Transacton B, Engneerng, ol. 30, No. B6, 789-794 rnted n The Islamc Republc of Iran, 006 Shraz Unversty "Research Note" ALICATION OF CHARGE SIMULATION METHOD TO ELECTRIC

More information

Prediction of Stock Market Index Movement by Ten Data Mining Techniques

Prediction of Stock Market Index Movement by Ten Data Mining Techniques Vol. 3, o. Modern Appled Scence Predcton of Stoc Maret Index Movement by en Data Mnng echnques Phchhang Ou (Correspondng author) School of Busness, Unversty of Shangha for Scence and echnology Rm 0, Internatonal

More information

Methodology to Determine Relationships between Performance Factors in Hadoop Cloud Computing Applications

Methodology to Determine Relationships between Performance Factors in Hadoop Cloud Computing Applications Methodology to Determne Relatonshps between Performance Factors n Hadoop Cloud Computng Applcatons Lus Eduardo Bautsta Vllalpando 1,2, Alan Aprl 1 and Alan Abran 1 1 Department of Software Engneerng and

More information

Optimal Bidding Strategies for Generation Companies in a Day-Ahead Electricity Market with Risk Management Taken into Account

Optimal Bidding Strategies for Generation Companies in a Day-Ahead Electricity Market with Risk Management Taken into Account Amercan J. of Engneerng and Appled Scences (): 8-6, 009 ISSN 94-700 009 Scence Publcatons Optmal Bddng Strateges for Generaton Companes n a Day-Ahead Electrcty Market wth Rsk Management Taken nto Account

More information

A Lyapunov Optimization Approach to Repeated Stochastic Games

A Lyapunov Optimization Approach to Repeated Stochastic Games PROC. ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING, OCT. 2013 1 A Lyapunov Optmzaton Approach to Repeated Stochastc Games Mchael J. Neely Unversty of Southern Calforna http://www-bcf.usc.edu/

More information

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING Matthew J. Lberatore, Department of Management and Operatons, Vllanova Unversty, Vllanova, PA 19085, 610-519-4390,

More information

FORMAL ANALYSIS FOR REAL-TIME SCHEDULING

FORMAL ANALYSIS FOR REAL-TIME SCHEDULING FORMAL ANALYSIS FOR REAL-TIME SCHEDULING Bruno Dutertre and Vctora Stavrdou, SRI Internatonal, Menlo Park, CA Introducton In modern avoncs archtectures, applcaton software ncreasngly reles on servces provded

More information

LIFETIME INCOME OPTIONS

LIFETIME INCOME OPTIONS LIFETIME INCOME OPTIONS May 2011 by: Marca S. Wagner, Esq. The Wagner Law Group A Professonal Corporaton 99 Summer Street, 13 th Floor Boston, MA 02110 Tel: (617) 357-5200 Fax: (617) 357-5250 www.ersa-lawyers.com

More information

DO LOSS FIRMS MANAGE EARNINGS AROUND SEASONED EQUITY OFFERINGS?

DO LOSS FIRMS MANAGE EARNINGS AROUND SEASONED EQUITY OFFERINGS? DO LOSS FIRMS MANAGE EARNINGS AROUND SEASONED EQUITY OFFERINGS? Fernando Comran, Unversty of San Francsco, School of Management, 2130 Fulton Street, CA 94117, Unted States, fcomran@usfca.edu Tatana Fedyk,

More information