PREDICTING CORPORATE BANKRUPTCY WITH SUPPORT VECTOR MACHINES


 Dinah Atkins
 2 years ago
 Views:
Transcription
1 1 PREDICTING CORPORATE BANKRUPTCY WITH SUPPORT VECTOR MACHINES Wlfgang HÄRDLE 2,3 Ruslan MORO 1,2 Drthea SCHÄFER 1 1 Deutsches Institut für Wirtschaftsfrschung (DIW) 2 HumbldtUniversität zu Berlin 3 Center fr Applied Statistics and Ecnmics (CASE) Predicting Crprate Bankruptcy with SVMs
2 Mtivatin 2 Mtivatin Crprate Bankruptcy Des a cmpany survive r g bankrupt within the predictin perid? Are there any changes in the dynamics f its indicatrs? Predicting Crprate Bankruptcy with SVMs
3 Mtivatin 3 Available Infrmatin fundamental indicatrs ptin and stck trading data annuncements macrecnmic indicatrs crprate gvernance principles emplyee prfiles epert assessments Predicting Crprate Bankruptcy with SVMs
4 Mtivatin 4 Applicatins estimating bankruptcy risks cmpany bnd rating (e.g. AAA, C, BB) based n the default prbability lss given default (LGD) estimatin (Basel II) pricing f nntraded cmpanies (IPOs, private cmpanies) Predicting Crprate Bankruptcy with SVMs
5 Mtivatin 5 General Questins What structural changes are typical fr failing cmpanies? What indicatrs are mst useful fr predicting default? What methds shuld be used t etract maimum infrmatin cntained in the perfrmance indicatrs? stck and ptin markets epert assessment statistical tls Predicting Crprate Bankruptcy with SVMs
6 Mtivatin 6 Bankruptcy Predictin Methds Multivariate discriminant analysis Beaver (1966), Altman (1968) Zscre: Z i = a 1 i1 + a 2 i a d id = a i, where i = ( i1,..., id ) R d are financial ratis fr the ith cmpany. successful cmpany: failure: Z i z Z i < z Predicting Crprate Bankruptcy with SVMs
7 Mtivatin 7 Linear Discriminant Analysis X 1 X 2 Surviving cmpanies Failing cmpanies Predicting Crprate Bankruptcy with SVMs
8 Mtivatin 8 Linear Discriminant Analysis Failing cmpanies Surviving cmpanies Distributin density Z Predicting Crprate Bankruptcy with SVMs
9 Mtivatin 9 Bankruptcy Predictin Methds (cnt.) Prbit mdel Martin (1977), Ohlsn (1980) E[y i i ] = Φ (a 0 + a 1 i1 + a 2 i a d id ), y i = {0, 1} Lgit mdel E[y i i ] = ep(a 0 + a 1 i a d id ) 1 + ep(a 0 + a 1 i a d id ) Gambler s ruin Wilc (1971) Recursive partitining Frydman et al. (1985) Neural netwrks (1990 s) Predicting Crprate Bankruptcy with SVMs
10 Mtivatin 10 Linearly Nnseparable Classificatin Prblem X 1 X 2 Surviving cmpanies Failing cmpanies Predicting Crprate Bankruptcy with SVMs
11 Mtivatin 11 The Benchmark Mdy s Mdel E[y i i ] = Φ{a 0 + d a j f j ( ij )} j=1 f j are estimated nnparametrically n univariate mdels Predicting Crprate Bankruptcy with SVMs
12 Outline f the Talk 12 Outline f the Talk 1. Mtivatin 2. Supprt Vectr Machines and Their Optimal Prperties 3. Epected Risk vs. Empirical Risk Minimizatin 4. Realizatin f SVMs 5. Nnlinear Case 6. Cmpany Classificatin with SVMs Predicting Crprate Bankruptcy with SVMs
13 Supprt Vectr Machines and their Optimal Prperties 13 Supprt Vectr Machines (SVMs) SVMs are a grup f methds fr classificatin and regressin that make use f classifiers prviding high margin. SVMs pssess a fleible structure which is nt chsen a priri Optimality f SVMs is given by the statistical learning thery SVMs d nt rely n asympttic prperties; they are ptimal fr small samples, i.e. in mst practically significant cases SVMs always give a unique slutin Predicting Crprate Bankruptcy with SVMs
14 Supprt Vectr Machines and their Optimal Prperties 14 Classificatin Prblem Training set: {( i, y i )} n i=1 with the distributin P ( i, y i ). Find the class y f a new bject using the classifier f : X {±1}, such that the epected risk R(f) is minimal. i is the vectr f the ith bject characteristics; y i { 1, +1} r {0, 1} is the class f the ith bject. Regressin Prblem Setup as fr the classificatin prblem but: y R Predicting Crprate Bankruptcy with SVMs
15 Epected Risk vs. Empirical Risk Minimizatin 15 Epected Risk Minimizatin If P (, y) is knwn, then the epected risk R(f) = 1 2 f() y dp (, y) = E P (,y)[l] can be minimized directly ver P (, y) f pt = arg min f F R(f) The lss L = 1 2 f() y = 0 if classificatin is crrect = 1 if classificatin is wrng F is the set f (nn)linear classifier functins Predicting Crprate Bankruptcy with SVMs
16 Epected Risk vs. Empirical Risk Minimizatin 16 Empirical Risk Minimizatin In practice P (, y) is usually unknwn: use Empirical Risk ˆR(f) = 1 n n i=1 1 2 f( i) y i Minimizatin (ERM) ver the training set {( i, y i )} n i=1 ˆf n = arg min f F ˆR(f) Predicting Crprate Bankruptcy with SVMs
17 Epected Risk vs. Empirical Risk Minimizatin 17 Empirical Risk vs. Epected Risk Risk R ˆ R emp ˆ R emp (f) R (f) f f pt f n ˆ Functin class Predicting Crprate Bankruptcy with SVMs
18 Epected Risk vs. Empirical Risk Minimizatin 18 Cnvergence Frm the law f large numbers lim n ˆR(f) = R(f) In additin ERM satisfies lim min n f F ˆR(f) = min f F R(f) if F is nt t big. Predicting Crprate Bankruptcy with SVMs
19 Epected Risk vs. Empirical Risk Minimizatin 19 VapnikChervnenkis (VC) Bund This is a basic result f the Statistical Learning Thery that already started in the 1960s: ( R(f) ˆR(f) h + φ n, ln(η) ) n when the bund hlds with prbability 1 η and φ ( h n, ln(η) ) n = h(ln 2n h + 1) ln( η 4 ) n Minimize VC bund Structural Risk Minimizatin search fr the ptimal mdel structure described by S h F; f S h. Predicting Crprate Bankruptcy with SVMs
20 Epected Risk vs. Empirical Risk Minimizatin 20 VapnikChervnenkis (VC) Dimensin Definitin. h is VC dimensin f a set f functins if there eists a set f pints { i } h i=1 such that these pints can be separated in all 2h pssible cnfiguratins, and n set { i } q i=1 eists where q > h satisfies this prperty. Eample 1. The functins A sin θ has an infinite VC dimensin. Eample 2. Three pints n a plane can be shattered by a set f linear indicatr functins in 2 h = 2 3 = 8 ways (whereas 4 pints cannt be shattered in 2 h = 2 4 = 16 ways). The VC dimensin equals h = 3. Predicting Crprate Bankruptcy with SVMs
21 Epected Risk vs. Empirical Risk Minimizatin 21 VC Dimensin (cnt.) Predicting Crprate Bankruptcy with SVMs
22 Realizatin f the SVMs 22 Linear SVMs. Separable Case The training set: {( i, y i )} n i=1, y i = {±1}, i R d. Find the classifier with the highest margin. Predicting Crprate Bankruptcy with SVMs
23 Realizatin f the SVMs 23 Let w + b = 0 be a separating hyperplane. Then d + (d ) will be the shrtest distance t the clsest bjects frm the classes +1 ( 1). i w + b +1 fr y i = +1 i w + b 1 fr y i = 1 cmbine them int ne cnstraint y i ( i w + b) 1 0 i (1) The cannical hyperplanes i w + b = ±1 are parallel and the distance between each f the them and the separating hyperplane is d ± = 1/ w. Predicting Crprate Bankruptcy with SVMs
24 Realizatin f the SVMs 24 Linear SVMs. Separable Case The margin is d + + d = 2/ w. T maimize it minimize the Euclidean nrm w subject t the cnstraint (1). Predicting Crprate Bankruptcy with SVMs
25 Realizatin f the SVMs 25 The Lagrangian Frmulatin The Lagrangian fr the primal prblem L P = 1 2 w 2 n α i {y i ( i w + b) 1} i=1 The KarushKuhnTucker (KKT) Cnditins L P w k = 0 n i=1 α iy i ik = 0 k = 1,..., d L P b = 0 n i=1 α iy i = 0 y i ( i w + b) 1 0 α i 0 i = 1,..., n α i {y i ( i w + b) 1} = 0 Predicting Crprate Bankruptcy with SVMs
26 Realizatin f the SVMs 26 Substitute the KKT cnditins int L and btain the Lagrangian fr the dual prblem L D = n α i 1 2 i=1 n i=1 n α i α j y i y j i j j=1 The primal and dual prblems are min ma L P w k,b α i s.t. α i 0 ma α i L D n α i y i = 0 i=1 Since the ptimizatin prblem is cnve the dual and primal frmulatins give the same slutin. Predicting Crprate Bankruptcy with SVMs
27 Realizatin f the SVMs 27 The Classificatin Stage The classifier functin is: where w = n i=1 α iy i i b = 1 2 ( + + ) w f() = sign( w + b) + and are any supprt vectrs frm each class subject t the cnstraints. α i = arg ma α i L D Predicting Crprate Bankruptcy with SVMs
28 Realizatin f the SVMs 28 Linear SVMs. Nnseparable Case In the nnseparable case it is impssible t separate the data pints with hyperplanes withut an errr. Predicting Crprate Bankruptcy with SVMs
29 Realizatin f the SVMs 29 The prblem can be slved by intrducing the psitive variables {ξ i } n i=1 in the cnstraints i w + b 1 ξ i fr y i = 1 i w + b 1 + ξ i fr y i = 1 ξ i 0 i If ξ i > 1, an errr ccurs. The bjective functin in this case is 1 2 w 2 + C( n ξ i ) ν i=1 where ν is a psitive integer cntrlling sensitivity t utliers C cntrls the generalizatin pwer Under such a frmulatin the prblem is cnve. Predicting Crprate Bankruptcy with SVMs
30 Realizatin f the SVMs 30 The Lagrangian Frmulatin The Lagrangian fr the primal prblem fr ν = 1: L P = 1 2 w 2 + C n ξ i n α i {y i ( i w + b) 1 + ξ i } n ξ i µ i i=1 i=1 i=1 The primal prblem: min w k,b,ξ i ma α i,µ i L P Predicting Crprate Bankruptcy with SVMs
31 Realizatin f the SVMs 31 The KKT Cnditins L P w k = 0 w k = n i=1 α iy i ik k = 1,..., d L P b = 0 n i=1 α iy i = 0 L P ξ i = 0 C α i µ i = 0 y i ( i w + b) 1 + ξ i 0 ξ i 0 α i 0 µ i 0 α i {y i ( i w + b) 1 + ξ i} = 0 µ i ξ i = 0 Predicting Crprate Bankruptcy with SVMs
32 Realizatin f the SVMs 32 Fr ν = 1 the dual Lagrangian will nt cntain ξ i r their Lagrange multipliers L D = n α i 1 2 n n α i α j y i y j i j (2) i=1 i=1 j=1 The dual prblem is subject t ma α i L D 0 α i C n α i y i = 0 i=1 Predicting Crprate Bankruptcy with SVMs
33 Nnlinear Case 33 Linear SVM. Nnseparable Case Predicting Crprate Bankruptcy with SVMs
34 Nnlinear Case 34 Nnlinear SVMs Map the data int the Hilbert space H and perfrm classificatin there Ψ : R d H Ntice, that in the Lagrangian frmulatin (2) the training data appear nly in the frm f dt prducts i j, which can be mapped int Ψ( i ) Ψ( j ). If a kernel functin K eists such that K( i, j ) = Ψ( i ) Ψ( j ), then we can use K withut knwing Ψ eplicitly. Predicting Crprate Bankruptcy with SVMs
35 Nnlinear Case 35 Mercer s Cnditin (1909) A necessary and sufficient cnditin fr a symmetric functin K( i, j ) t be a kernel is that it must be psitive definite, i.e. fr any data set 1,..., n and any real numbers λ 1,..., λ n the functin K must satisfy n i=1 n λ i λ j K( i, j ) 0 j=1 Sme eamples f kernel functins: K( i, j ) = e i j 2 /2σ 2 Gaussian kernel K( i, j ) = ( i j + 1) p K( i, j ) = tanh(k i j δ) plynmial kernel hyperblic tangent kernel Predicting Crprate Bankruptcy with SVMs
36 Nnlinear Case 36 Classes f Kernels A statinary kernel is the kernel which is translatin invariant K( i, j ) = K S ( i j ) An istrpic (hmgeneus) kernel is ne which depends nly n the nrm f the lag vectr (distance) between tw data pints K( i, j ) = K I ( i j ) A lcal statinary kernel is the kernel f the frm K( i, j ) = K 1 ( i + j 2 )K 2 ( i j ) where K 1 is a nnnegative functin, K 2 is a statinary kernel. Predicting Crprate Bankruptcy with SVMs
37 Nnlinear Case 37 Matérn kernel K I ( i j ) K I (0) = 1 2 ν 1 Γ(ν) (2 ν i j θ ) ν H ν ( 2 ν i j ) θ where Γ is the Gamma functin and H ν is the mdified Bessel functin f the secnd kind f rder ν. The parameter ν allws t cntrl the smthness. The Matérn kernel reduces t the Gaussian kernel fr ν. Predicting Crprate Bankruptcy with SVMs
38 Cmpany Classificatin with SVMs 38 Cmpany Analysis Surce: annual reprts f the cmpanies frm available thrugh the Securities and Echange Cmmisin (SEC) (www.sec.gv) n= cmpanies survived and 42 cmpanies went bankrupt by The failing and surviving cmpanies were matched in size and industry. The bankruptcy was declared by filing Chapter 11 f the Bankruptcy Cde. Predicting Crprate Bankruptcy with SVMs
39 Cmpany Classificatin with SVMs 39 The cmpanies were characterized by 14 variables frm which the fllwing financial ratis were calculated: 1. Prfit measures: EBIT/TA, NI/TA, EBIT/Sales; 2. Leverage ratis: EBIT/Interest, TD/TA, TL/TA; 3. Liquidity ratis: QA/CL, Cash/TA, WC/TA, CA/CL, STD/TD. 4. Activity r turnver ratis: Sales/TA, Inventries/COGS. The average capitalizatin f a cmpany: $8.12 bln. d = 14 Predicting Crprate Bankruptcy with SVMs
40 Cmpany Classificatin with SVMs 40 Cluster Analysis f the Cmpanies Operating Bankrupt EBIT/TA NI/TA EBIT/Sales EBIT/INT TD/TA TL/TA SIZE Predicting Crprate Bankruptcy with SVMs
41 Cmpany Classificatin with SVMs 41 Operating Bankrupt QA/CL CASH/TA WC/TA CA/CL STD/TD Sales/TA INV/COGS There are 19 members in the cluster f survived cmpanies and 65 members in cluster f failed cmpanies. The result significantly changes in the presence f utliers. Predicting Crprate Bankruptcy with SVMs
42 Cmpany Classificatin with SVMs 42 Cmpany Classificatin with SVMs. The Influence f Different Classifier Cmpleities Predicting Crprate Bankruptcy with SVMs
43 Cmpany Classificatin with SVMs 43 Leverage (TL/TA) Prfitability (NI/TA) Figure 1: The case f a lw cmpleity f classificatin functins (near linear functins are used, the radial basis is 20Σ 1/2 ). The generalizatin ability is fied (C = 1). Predicting Crprate Bankruptcy with SVMs
44 Cmpany Classificatin with SVMs 44 Leverage (TL/TA) Prfitability (NI/TA) Figure 2: The case f an average cmpleity f the classifier functins (the radial basis is 2Σ 1/2 ). The generalizatin ability is fied (C = 1) Predicting Crprate Bankruptcy with SVMs
45 Cmpany Classificatin with SVMs 45 Leverage (TL/TA) Prfitability (NI/TA) Figure 3: The case f a highly cmple classificatin functins (the radial basis is 0.53Σ 1/2 ). The generalizatin ability is fied (C = 1) Predicting Crprate Bankruptcy with SVMs
46 Cmpany Classificatin with SVMs 46 Cmpany Classificatin with SVMs. The Influence f Different Generalizatin Abilities Predicting Crprate Bankruptcy with SVMs
47 Cmpany Classificatin with SVMs 47 Leverage (TL/TA) Prfitability (NI/TA) Figure 4: The case f a very high generalizatin ability (C = 0.01). The radial basis is fied at 2Σ 1/2 Predicting Crprate Bankruptcy with SVMs
48 Cmpany Classificatin with SVMs 48 Leverage (TL/TA) Prfitability (NI/TA) Figure 5: The case f an average generalizatin ability (C = 1). The radial basis is fied at 2Σ 1/2 Predicting Crprate Bankruptcy with SVMs
49 Cmpany Classificatin with SVMs 49 Leverage (TL/TA) Prfitability (NI/TA) Figure 6: The case f lw generalizatin ability (C = 100). The radial basis is fied at 2Σ 1/2 Predicting Crprate Bankruptcy with SVMs
Forecasting Corporate Distress in the Asian and Pacific Region
Frecasting Crprate Distress in the Asian and Pacific Regin Russ Mr, Wlfgang Härdle, Saeideh Aliakbari, Linda Hffmann The authrs are grateful fr the financial supprt, data access and ecellent research facilities
More informationLecture 2: Supervised vs. unsupervised learning, biasvariance tradeoff
Lecture 2: Supervised vs. unsupervised learning, biasvariance tradeff Reading: Chapter 2 Stats 202: Data Mining and Analysis Lester Mackey September 23, 2015 (Slide credits: Sergi Bacallad) 1 / 24 Annuncements
More informationSupport Vector and Kernel Machines
Supprt Vectr and Kernel Machines Nell Cristianini BIOwulf Technlgies nell@supprtvectr.net http:///tutrial.html ICML 2001 A Little Histry SVMs intrduced in COLT92 by Bser, Guyn, Vapnik. Greatly develped
More informationSAP Predictive Maintenance and Service, onpremise edition and Data Science. Customer
SAP Predictive Maintenance and Service, npremise editin and Data Science Custmer Predictive Maintenance is a prcess, nt just an algrithm Dmain expertise is as imprtant as data science, if nt mre * * *
More informationHP Point of Sale FAQ Warranty, Care Pack Service & Support. Limited warranty... 2 HP Care Pack Services... 3 Support... 3
HP Pint f Sale FAQ Warranty, Care Pack Service & Supprt Limited warranty... 2 HP Care Pack Services... 3 Supprt... 3 Limited warranty Q: What des a 3/3/3 limited warranty mean? A: HP Retail Pint f Sale
More informationECLT5810 ECommerce Data Mining Techniques SAS Enterprise Miner Neural Network
Enterprise Miner Neural Netwrk 1 ECLT5810 ECmmerce Data Mining Techniques SAS Enterprise Miner Neural Netwrk A Neural Netwrk is a set f cnnected input/utput units where each cnnectin has a weight assciated
More informationTraffic monitoring on ProCurve switches with sflow and InMon Traffic Sentinel
An HP PrCurve Netwrking Applicatin Nte Traffic mnitring n PrCurve switches with sflw and InMn Traffic Sentinel Cntents 1. Intrductin... 3 2. Prerequisites... 3 3. Netwrk diagram... 3 4. sflw cnfiguratin
More informationChapter 3: Cluster Analysis
Chapter 3: Cluster Analysis 3.1 Basic Cncepts f Clustering 3.1.1 Cluster Analysis 3.1. Clustering Categries 3. Partitining Methds 3..1 The principle 3.. KMeans Methd 3..3 KMedids Methd 3..4 CLARA 3..5
More informationApplied Spatial Statistics: Lecture 6 Multivariate Normal
Applied Spatial Statistics: Lecture 6 Multivariate Nrmal Duglas Nychka, Natinal Center fr Atmspheric Research Supprted by the Natinal Science Fundatin Bulder, Spring 2013 Outline additive mdel Multivariate
More informationImproved Data Center Power Consumption and Streamlining Management in Windows Server 2008 R2 with SP1
Imprved Data Center Pwer Cnsumptin and Streamlining Management in Windws Server 2008 R2 with SP1 Disclaimer The infrmatin cntained in this dcument represents the current view f Micrsft Crpratin n the issues
More informationReleased Test Answer and Alignment Document Mathematics Algebra 1 Performance Based Assessment
Released Test Answer and Alignment Dcument Mathematics Algebra 1 Perfrmance Based Assessment The fllwing pages include the answer key fr all machinescred items, fllwed by the rubrics fr the handscred
More informationSAS PORTFOLIO ANALYSIS: RANDOM PORTFOLIOS FOR EVALUATING TRADING
SAS Applicatin: develpment SAS PORTFOLIO ANALYSIS: RANDOM PORTFOLIOS FOR EVALUATING TRADING PAUWELS STEFAAN ECKERMAN EWOUT ABSTRACT Prtfli pprtunity distributins can prvide a statistical test that a trading
More informationIndustrial and Systems Engineering Master of Science Program Data Analytics and Optimization
Industrial and Systems Engineering Master f Science Prgram Data Analytics and Optimizatin Department f Integrated Systems Engineering The Ohi State University (Expected Duratin: 3 Semesters) Our sciety
More informationSystem Business Continuity Classification
System Business Cntinuity Classificatin Business Cntinuity Prcedures Infrmatin System Cntingency Plan (ISCP) Business Impact Analysis (BIA) System Recvery Prcedures (SRP) Cre Infrastructure Criticality
More informationInstitutional Finance
Institutinal Finance Lecture 08 : Liquidity, Limits t Arbitrage Intr (Merger Arbitrage) Markus K. Brunnermeier Preceptr: Dng Bem Chi Princetn University 1 Cnvergence trades (pairs trading), statistical
More informationFirewall/Proxy Server Settings to Access Hosted Environment. For Access Control Method (also known as access lists and usually used on routers)
Firewall/Prxy Server Settings t Access Hsted Envirnment Client firewall settings in mst cases depend n whether the firewall slutin uses a Stateful Inspectin prcess r ne that is cmmnly referred t as an
More informationwww.firebrandtraining.cm Abut NAV 2013 Cre Setup & Finance: The certificatin cnsists f tpics frm the fllwing curses: 80436: C/SIDE Intrductin in Micrsft Dynamics NAV 2013 80437: C/SIDE Slutin Develpment
More informationexpertise hp services valupack consulting description security review service for Linux
expertise hp services valupack cnsulting descriptin security review service fr Linux Cpyright services prvided, infrmatin is prtected under cpyright by HewlettPackard Cmpany Unpublished Wrk  ALL RIGHTS
More information2. When logging is used, which severity level indicates that a device is unusable?
Last updated by Admin at March 3, 2015. 1. What are the mst cmmn syslg messages? thse that ccur when a packet matches a parameter cnditin in an access cntrl list link up and link dwn messages utput messages
More informationReleased Test Answer and Alignment Document Mathematics Grade 8 Performance Based Assessment
Released Test Answer and Alignment Dcument Mathematics Grade 8 Perfrmance Based Assessment The fllwing pages include the answer key fr all machinescred items, fllwed by the rubrics fr the handscred items.
More informationData Science. IRDS: Data Mining Process. The term data mining. The term data mining
Science IRDS: Mining Prcess Charles Suttn Universit f Edinburgh Our rking definitin science is the stud f the cmputatinal principles, methds, and sstems fr etracting knledge frm data. A relativel ne term.
More informationWelcome to CNIPS Training: CACFP Claim Entry
Welcme t CNIPS Training: CACFP Claim Entry General Cmments frm SCN CACFP claiming begins with submissin f the Octber claim due by Nvember 15, 2012. Timelines/Due Dates With CNIPS, SCN will cntinue t enfrce
More informationMcAfee Enterprise Security Manager. Data Source Configuration Guide. Infoblox NIOS. Data Source: September 2, 2014. Infoblox NIOS Page 1 of 8
McAfee Enterprise Security Manager Data Surce Cnfiguratin Guide Data Surce: Infblx NIOS September 2, 2014 Infblx NIOS Page 1 f 8 Imprtant Nte: The infrmatin cntained in this dcument is cnfidential and
More informationTechnical White Paper
The Data Integrity Imperative If it isn t accurate, it isn t available. Technical White Paper Visin Slutins, Inc. Intrductin The fundamental requirement f high availability sftware is t ensure that critical
More informationGothaer Versicherungen bases its insurance quotation software on the b+m Generative Development Process and the b+m ArchitectureWare product line
Gthaer Versicherungen bases its insurance qutatin sftware n the b+m Generative Develpment Prcess and the b+m ArchitectureWare prduct line Field f Business Insurance slutins fr the banking sectr. Applicatin
More informationLABOR PRODUCTIVITY AS A FACTOR FOR BANKRUPTCY PREDICTION
Daniel BRÎNDESCU OLARIU West University f Timisara LABOR PRODUCTIVITY AS A FACTOR FOR BANKRUPTCY PREDICTION Empirical study Keywrds Crprate finance Risk Failure Financial rati Financial analysis Classificatin
More informationHarePoint HelpDesk for SharePoint. For SharePoint Server 2010, SharePoint Foundation 2010. User Guide
HarePint HelpDesk fr SharePint Fr SharePint Server 2010, SharePint Fundatin 2010 User Guide Prduct versin: 14.1.0 04/10/2013 2 Intrductin HarePint.Cm (This Page Intentinally Left Blank ) Table f Cntents
More informationSTIOffice Integration Installation, FAQ and Troubleshooting
STIOffice Integratin Installatin, FAQ and Trubleshting Installatin Steps G t the wrkstatin/server n which yu have the STIDistrict Net applicatin installed. On the STI Supprt page at http://supprt.stik12.cm/,
More informationOnline Service Reservations for Enterprise Agreements
MAY 2016 Service Center Online Service Reservatins fr Enterprise Agreements 2 Online Service Reservatins fr Enterprise Agreements MICROSOFT VOLUME LICENSING SERVICE CENTER TASKS 3 Online Services Custmer
More informationAP Calculus BC. Revised: Aug 11, 2009
Curse name: AP Calculus BC Revised: Aug 11, 2009 Curse Descriptin: In AP Calculus BC, students will explre fur main ideas frm calculus: limits, derivatives, indefinite integrals, and definite integrals.
More informationPENNSYLVANIA SURPLUS LINES ASSOCIATION Electronic Filing System (EFS) Frequently Asked Questions and Answers
PENNSYLVANIA SURPLUS LINES ASSOCIATION Electrnic Filing System (EFS) Frequently Asked Questins and Answers 1 What changed in Release 2.0?...2 2 Why was my accunt disabled?...3 3 Hw d I inactivate an accunt?...4
More informationImplementing SQL Manage Quick Guide
Implementing SQL Manage Quick Guide The purpse f this dcument is t guide yu thrugh the quick prcess f implementing SQL Manage n SQL Server databases. SQL Manage is a ttal management slutin fr Micrsft SQL
More informationData mining methodology extracts hidden predictive information from large databases.
Data Mining Overview By: Dr. Michael Gilman, CEO, Data Mining Technlgies Inc. With the prliferatin f data warehuses, data mining tls are flding the market. Their bjective is t discver hidden gld in yur
More informationService Engineering  Recitation 11. 4CallCenters Software
Service Engineering  Recitatin 11 4CallCenters Sftware Dwnlad and Install setup.exe and help dcument available frm http://ie.technin.ac.il/serveng/4callcenters/dwnlads.htm 2 Tls Perfrmance Prfiler Anticipating
More informationSchedule 2b. additional terms for Managed Video Service 1. SERVICE DESCRIPTION
additinal terms fr Managed Vide Service 1. SERVICE DESCRIPTION Interute s Managed Vide Service prvides pinttpint and multipint vide cnferencing fr cmmunicatin between bth the Custmer s ffices and external
More informationSpatial basis risk and feasibility of index based crop insurance in Canada: A spatial panel data econometric approach
Spatial basis risk and feasibility f index based crp insurance in Canada: A spatial panel data ecnmetric apprach Millin A.Tadesse (Ph.D.), University f Waterl, Statistics and Actuarial Science, Canada.
More informationService Desk Self Service Overview
Tday s Date: 08/28/2008 Effective Date: 09/01/2008 Systems Invlved: Audience: Tpics in this Jb Aid: Backgrund: Service Desk Service Desk Self Service Overview All Service Desk Self Service Overview Service
More informationElectronic Data Interchange (EDI) Requirements
Electrnic Data Interchange (EDI) Requirements 1.0 Overview 1.1 EDI Definitin 1.2 General Infrmatin 1.3 Third Party Prviders 1.4 EDI Purchase Order (850) 1.5 EDI PO Change Request (860) 1.6 Advance Shipment
More informationUsing Sentrygo Enterprise/ASPX for Sentrygo Quick & Plus! monitors
Using Sentryg Enterprise/ASPX fr Sentryg Quick & Plus! mnitrs 3Ds (UK) Limited, February, 2014 http://www.sentryg.cm Be Practive, Nt Reactive! Intrductin Sentryg Enterprise Reprting is a selfcntained
More informationIT Essentials (ITE v6.0) Chapter 6 Exam Answers 100% 2016
IT Essentials (ITE v6.0) Chapter 6 Exam Answers 100% 2016 1. What wuld be a reasn fr a cmputer user t use the Task Manager Perfrmance tab? t increase the perfrmance f the CPU t view the prcesses that are
More informationMorgan County REQUEST FOR PROPOSAL 20160211010 PROJECT NAME: GIS TECHNICAL SUPPORT AND DEVELOPMENT SERVICES
Mrgan Cunty REQUEST FOR PROPOSAL 20160211010 PROJECT NAME: GIS TECHNICAL SUPPORT AND DEVELOPMENT SERVICES Mrgan Cunty 218 West Kiwa Avenue, P.O. Bx 596 Frt Mrgan, Clrad 80701 PH: 9705423500, ext. 1410
More informationNuclear Chemistry: Rates of Radioactive Decay
Activity 48 Nuclear Chemistry: Rates f Radiactive Decay What D Yu Think? Radiactive idine131 is used t treat thyrid cancer. A patient is given 20.0 mg f idine131 in the frm f NaI, and after 8 days nly
More informationCORPORATIONS LAW SUMMARY
CORPORATIONS LAW SUMMARY LAWSKOOL PTY LTD Cntents INTRODUCTION 5 Frms f Legal Assciatin 5 Administrative and Legislative Structure f Australian 5 Crpratins Law SEPARATE LEGAL ENTITY 7 Classifying Cmpanies
More informationImplementing ifolder Server in the DMZ with ifolder Data inside the Firewall
Implementing iflder Server in the DMZ with iflder Data inside the Firewall Nvell Cl Slutins AppNte www.nvell.cm/clslutins JULY 2004 OBJECTIVES The bjectives f this dcumentatin are as fllws: T cnfigure
More informationSQL Perform Tools 5.10 Release Note
SQL Perfrm Tls 5.10 Release Nte Lndn, UK, February 26 2015 SQL Perfrm Tls versin 5.10 release Tday we are prudly annuncing the latest release f ur prducts' family SQL Perfrm Tls. Fr clarity, the prduct
More informationMarketing Consultancy Division (MCD) Export Consultancy Unit (ECU) Export in Focus. Export Market Expansion Strategies. RabiI, 1427 (April, 2006)
Marketing Cnsultancy Divisin (MCD) Exprt Cnsultancy Unit (ECU) Exprt in Fcus Exprt Market Expansin Strategies RabiI, 1427 (April, 2006) 1 Exprt Market Expansin Strategies Intrductin It is clear that glbalizatin
More informationHP ExpertOne. HP2T21: Administering HP Server Solutions. Table of Contents
HP ExpertOne HP2T21: Administering HP Server Slutins Industry Standard Servers Exam preparatin guide Table f Cntents Overview 2 Why take the exam? 2 HP ATP Server Administratr V8 certificatin 2 Wh shuld
More informationHW4 Software version 3. Humidity and Temperature Adjustment AirChip 3000 devices
Page 1 f 25 HW4 Sftware versin 3 Humidity and Temperature Adjustment AirChip 3000 devices Page 2 f 25 Table f cntents 1 ORGANIZATION OF THE HW4 MANUALS... 3 2 OVERVIEW... 4 3 SINGLE PROBE ADJUSTMENT...
More informationUNIVERSITY OF CALIFORNIA MERCED PERFORMANCE MANAGEMENT GUIDELINES
UNIVERSITY OF CALIFORNIA MERCED PERFORMANCE MANAGEMENT GUIDELINES REFERENCES AND RELATED POLICIES A. UC PPSM 2 Definitin f Terms B. UC PPSM 12 Nndiscriminatin in Emplyment C. UC PPSM 14 Affirmative
More informationLast time: search strategies
Last time: search strategies Uninfrmed: Use nly infrmatin available in the prblem frmulatin Breadthfirst Unifrmcst Depthfirst Depthlimited Iterative deepening Infrmed: Use heuristics t guide the search
More informationSAP Financials: Management Accounting
SAP Financials: Management Accunting The SAP Financials: Management Accunting curse cntains the fllwing training: SAP129 SAP Navigatin TERP01 SAP ERP Business Prcess Basics and Navigatin TERP20 SAP Financial
More informationFOCUS Service Management Software Version 8.4 for Passport Business Solutions Installation Instructions
FOCUS Service Management Sftware Versin 8.4 fr Passprt Business Slutins Installatin Instructins Thank yu fr purchasing Fcus Service Management Sftware frm RTM Cmputer Slutins. This bklet f installatin
More informationUnderstand Business Continuity
Understand Business Cntinuity Lessn Overview In this lessn, yu will learn abut: Business cntinuity Data redundancy Data availability Disaster recvery Anticipatry Set What methds can be emplyed by a system
More informationDerivative Markets and Instruments
1 Mdule # 6 Cmpnent # 1 This Cmpnent: fcuses n the basics f as part f ur examinatin f Derivatives. assumes a base level f financial thery, but attempts t add a level f practical applicatin. We attempt
More informationStatistical Analysis (1way ANOVA)
Statistical Analysis (1way ANOVA) Cntents at a glance I. Definitin and Applicatins...2 II. Befre Perfrming 1way ANOVA  A Checklist...2 III. Overview f the Statistical Analysis (1way tests) windw...3
More informationAnalytical Techniques created for the offline world can they yield benefits online?
Analytical Techniques created fr the ffline wrld can they yield benefits nline? Dr. Barry Leventhal BarryAnalytics Limited Transfrming Data Abut BarryAnalytics Advanced Analytics Cnsultancy funded in 2009
More information990 epostcard FAQ. Is there a charge to file form 990N (epostcard)? No, the epostcard system is completely free.
990 epstcard FAQ Fr frequently asked questins abut filing the epstcard that are nt listed belw, brwse the FAQ at http://epstcard.frm990.rg/frmtsfaq.asp# (cpy and paste this link t yur brwser). General
More informationNeural Networks. Neural Network. Neural Network. Neural Network. When NNs can be Used? Neural Networks
Neural Netwrks Neural Netwrk Andrew Kusiak 2139 Seamans Center Iwa Cit, IA 522421527 andrewkusiak@uiwa.edu http://www.icaen.uiwa.edu/~ankusiak Tel. 319335 5934 Input Age = 51 Temperature = 40C Neurn
More informationCompany XYZ Sample Data Cleansing Guidelines
Cmpany XYZ Sample Data Cleansing Guidelines Objective The purpse f this dcument is t utline the curse f actins t cleanse data in the legacy systems r in the crrespnding staging area befre it is laded int
More informationHow to Reduce Project Lead Times Through Improved Scheduling
Hw t Reduce Prject Lead Times Thrugh Imprved Scheduling PROBABILISTIC SCHEDULING & BUFFER MANAGEMENT Cnventinal Prject Scheduling ften results in plans that cannt be executed and t many surprises. In many
More informationAP COMPUTER SCIENCE A 2016 GENERAL SCORING GUIDELINES
AP COMPUTER SCIENCE A 2016 GENERAL SCORING GUIDELINES Apply the questin assessment rubric first, which always takes precedence. Penalty pints can nly be deducted in a part f the questin that has earned
More informationHOW TO SELECT A LIFE INSURANCE COMPANY
HOW TO SELECT A LIFE INSURANCE COMPANY There will prbably be hundreds f life insurance cmpanies t chse frm when yu decide t purchase a life insurance plicy. Hw d yu decide which ne? Mst cmpanies are quite
More informationSystem Business Continuity Classification
Business Cntinuity Prcedures Business Impact Analysis (BIA) System Recvery Prcedures (SRP) System Business Cntinuity Classificatin Cre Infrastructure Criticality Levels Critical High Medium Lw Required
More informationA how to guide on setting up a Project Management Office (PMO)
A hw t guide n setting up a Prject Management Office (PMO) By Peter Charquer Kestenhlz, Partner and Senir Business Cnsultant Versin 1.0 Released 9 March, 2011 Brief intrductin t the histry f the PMO Prject
More informationTOWARDS OF AN INFORMATION SERVICE TO EDUCATIONAL LEADERSHIPS: BUSINESS INTELLIGENCE AS ANALYTICAL ENGINE OF SERVICE
TOWARDS OF AN INFORMATION SERVICE TO EDUCATIONAL LEADERSHIPS: BUSINESS INTELLIGENCE AS ANALYTICAL ENGINE OF SERVICE A N D R E I A F E R R E I R A, A N T Ó N I O C A S T R O, D E L F I N A S Á S O A R E
More informationDisk Redundancy (RAID)
A Primer fr Business Dvana s Primers fr Business series are a set f shrt papers r guides intended fr business decisin makers, wh feel they are being bmbarded with terms and want t understand a cmplex tpic.
More informationExecution overview The macro level
Executin verview The macr level Cmpared t the micr level that we described earlier in The micr level dcument, macr is, as the wrd indicate executin n a higher level and it is clser t where it all starts;
More informationPAYMENT GATEWAY ACCOUNT SETUP FORM
PAYMENT GATEWAY ACCOUNT SETUP FORM Thank yu fr chsing us fr yur ecmmerce transactin needs. CyberSurce develps, perates and markets payment transactin prcessing services, as well as a hst f valueadding
More informationMiami University Sprint Class
Miami University Sprint Class Prewrk G t www.beanactuary.cm and read abut the actuarial prfessin. Week 1 Why d we need actuaries? Cmpanies sell prmises nt widgets. Lngterm nature. Tpic 1 Types f Insurance
More informationHow ISO 9001 and Support SarbanesOxley Compliance. By Sandford Liebesman
Change Management Cnsulting, Inc. Transfrming Businesses Wrldwide Hw ISO 9001 and 14001 Supprt SarbanesOxley Cmpliance By Sandfrd Liebesman Intrductin In September 2005, I published an article in Quality
More informationFOCUS Service Management Software Version 8.5 for Passport Business Solutions Installation Instructions
FOCUS Service Management Sftware fr Passprt Business Slutins Installatin Instructins Thank yu fr purchasing Fcus Service Management Sftware frm RTM Cmputer Slutins. This bklet f installatin instructins
More informationWinFlex Web Single SignOn (EbixLife XML Format) Version: 1.5
WinFlex Web Single SignOn (EbixLife XML Frmat) Versin: 1.5 The gal f this dcument is t specify and explre the basic peratins that are required t facilitate a vendr applicatin requesting access t the WinFlex
More informationData Warehouse: Introduction
DataBase and Data Mining Grup f Plitecnic di Trin DataBase and Data Mining Grup f Plitecnic di Trin DataBase and Data Mining Grup f Plitecnic di Trin DataBase and Data Mining Grup f Plitecnic di Trin DataBase
More informationSBClient and Microsoft Windows Terminal Server (Including Citrix Server)
SBClient and Micrsft Windws Terminal Server (Including Citrix Server) Cntents 1. Intrductin 2. SBClient Cmpatibility Infrmatin 3. SBClient Terminal Server Installatin Instructins 4. Reslving Perfrmance
More informationDetermining Efficient Solutions to Multiple. Objective Linear Programming Problems
Applied Mathematical Sciences, Vl. 7, 2013, n. 26, 12751282 HIKARI Ltd, www.mhikari.cm Determining Efficient Slutins t Multiple Objective Linear Prgramming Prblems P. Pandian and M. Jayalakshmi Department
More informationCompensation Texas Tax Code 171.1013 Rule 3.589
Cmpensatin Texas Tax Cde 171.1013 Rule 3.589 Presented by: Franchise Tax Plicy Staff Organizer: Janet Spies Panelists: Teresa Bstick, Claire Jamal, Jerry Oxfrd, Jennifer Specchi, and Bill Yrk Margin Cmpensatin
More informationViPNet VPN in Cisco Environment. Supplement to ViPNet Documentation
ViPNet VPN in Cisc Envirnment Supplement t ViPNet Dcumentatin 1991 2015 Inftecs Americas. All rights reserved. Versin: 0012104 90 02 ENU This dcument is included in the sftware distributin kit and is
More informationTraining Efficiency: Optimizing Learning Technology
Ideas & Insights frm 2008 Training Efficiency Masters Series Survey Results Training Efficiency: Optimizing Learning Technlgy trainingefficiency.cm Survey Results: Training Efficiency: Optimizing Learning
More informationFedACH Services via FedLine Web and FedACH Services via FedLine Advantage Participant Role
(FedLine Advantage nly) Send ACH payment files thrugh an easytuse brwserbased file transmissin system using a VPN tunnel t encrypt and secure infrmatin cntained in FedACH files USB tkens are used t authenticate
More informationTHE UNEARNED NO CLAIM BONUS. C. P. WELTEN Amsterdam
THE UNEARNED NO CLAIM BONUS C. P. WELTEN Amsterdam I. The claims experience f a mtrcar insurance is assumed t give sme indicatin abut the risk (basic claim frequency) f that insurance. The experience rating
More informationFund Accounting Class II
Fund Accunting Class II BS&A Fund Accunting Class II Cntents Gvernmental Financial Reprting Mdel  Minimum GAAP Reprting Requirements... 1 MD&A (Management's Discussin and Analysis)... 1 Basic Financial
More informationPROFESSIONAL PRACTICE VALUATION. Jane R. Smith, DDS. April 1, Prepared by:
PROFESSIONAL PRACTICE VALUATION Jane R. Smith, DDS April 1, 2015 Prepared by: 101 E. PARK BLVD. SUITE 300 PLANO, TX 75074 972.881.1501 www.dmeadvisrs.cm DEFINITION OF FAIR MARKET VALUE The fair market
More informationPA 14: Sustainable Investment
PA 14: Sustainable Investment 4 pints available A. Credit Ratinale This credit recgnizes institutins that use their investment pwer t prmte sustainability. There are a variety f appraches an institutin
More informationAras Innovator Internet Explorer Client Configuration
Aras Innvatr Internet Explrer Client Cnfiguratin Aras Innvatr 9.2 Dcument #: 9.2.012282009 Last Mdified: 4/1/2010 Aras Crpratin ARAS CORPORATION Cpyright 2010 All rights reserved Aras Crpratin 300 Brickstne
More informationMobile Device Manager Admin Guide. Reports and Alerts
Mbile Device Manager Admin Guide Reprts and Alerts September, 2013 MDM Admin Guide Reprts and Alerts i Cntents Reprts and Alerts... 1 Reprts... 1 Alerts... 3 Viewing Alerts... 5 Keep in Mind...... 5 Overview
More informationVersion: Modified By: Date: Approved By: Date: 1.0 Michael Hawkins October 29, 2013 Dan Bowden November 2013
Versin: Mdified By: Date: Apprved By: Date: 1.0 Michael Hawkins Octber 29, 2013 Dan Bwden Nvember 2013 Rule 4004J Payment Card Industry (PCI) Patch Management (prpsed) 01.1 Purpse The purpse f the Patch
More informationAnnex 3. Specification of requirement. Surveillance of sulphuremissions from ships in Danish waters
Annex 3 Specificatin f requirement Surveillance f sulphuremissins frm ships in Danish waters 1 Cntent 1 Objective... 3 2 Prject Perid... 4 3 Psitin and Planning f Measurements... 4 3.1 Mnitring frm a
More informationEmployee Engagement Business Case
Emplyee Engagement Business Case A Peple & Culture White Paper Emplyee Engagement Business Case Purpse This dcument is a mdule frm the Peple & Culture training curse n Strategic Emplyee Engagement. The
More informationRetirement Planning Options Annuities
Retirement Planning Optins Annuities Everyne wants a glden retirement. But saving fr retirement is n easy task. The baby bmer generatin is graying. Mre and mre peple are appraching retirement age. With
More informationeurex circular 178/05
eurex circular 178/05 Date: Frankfurt, September 26, 2005 Recipients: All Eurex members and vendrs, CCP members Authrized by: Peter Reitz U High Pririty Hurs Extensin n Eurex Exchanges (THX): Detailed
More informationICT Security: the real challenge is cyberdefence
Sicurezza Infrmatica: nulla è più difficile che difendere un sistema ICT Security: the real challenge is cyberdefence F.Baiardi Dipartiment di Infrmatica Università di Pisa Infrmally: Therem: Crashing
More informationTHE MICROFINANCE ASSOCIATION Training Programme London, UK
THE MICROFINANCE ASSOCIATION Training Prgramme 2016 Lndn, UK The Micrfinance Asscatin, Science and Innvatin Centre, NUCLEUS Brunel Way, DA1 5GA, United Kingdm Tel: +44 (0) 1322 312078 ade@micrfinanceaassciatin.rg
More informationResearch Report. Abstract: Data Center Networking Trends. January 2012. By Jon Oltsik With Bob Laliberte and Bill Lundell
Research Reprt Abstract: Data Center Netwrking Trends By Jn Oltsik With Bb Laliberte and Bill Lundell January 2012 2012 Enterprise Strategy Grup, Inc. All Rights Reserved. Intrductin Research Objective
More informationData Abstraction Best Practices with Cisco Data Virtualization
White Paper Data Abstractin Best Practices with Cisc Data Virtualizatin Executive Summary Enterprises are seeking ways t imprve their verall prfitability, cut csts, and reduce risk by prviding better access
More informationAras Innovator Internet Explorer Client Configuration
Aras Innvatr Internet Explrer Client Cnfiguratin Aras Innvatr 9.3 Dcument #: 9.3.012282009 Last Mdified: 6/10/2011 Aras Crpratin ARAS CORPORATION Cpyright 2011 All rights reserved Aras Crpratin 300 Brickstne
More informationURM 11g Implementation Tips, Tricks & Gotchas ALAN MACKENTHUN FISHBOWL SOLUTIONS, INC.
URM 11g Implementatin Tips, Tricks & Gtchas ALAN MACKENTHUN FISHBOWL SOLUTIONS, INC. i Fishbwl Slutins Ntice The infrmatin cntained in this dcument represents the current view f Fishbwl Slutins, Inc. n
More informationFermilab Time & Labor Desktop Computer Requirements
Fermilab Time & Labr Desktp Cmputer Requirements Fermilab s new electrnic time and labr reprting (FTL) system utilizes the Wrkfrce Central prduct frm Krns. This system is accessed using a web brwser utilizing
More informationTrends and Considerations in Currency Recycle Devices. What is a Currency Recycle Device? November 2003
Trends and Cnsideratins in Currency Recycle Devices Nvember 2003 This white paper prvides basic backgrund n currency recycle devices as cmpared t the cmbined features f a currency acceptr device and a
More informationTreasury Gateway Getting Started Guide
Treasury Gateway Getting Started Guide Treasury Gateway is a premier single signn and security prtal which allws yu access t multiple services simultaneusly thrugh the same sessin, prvides cnvenient access
More informationOverview. Some terminology. Classical statistics... Classical statistics... Classical statistics... SPM Kurs zur funktionellen Bildgebung
SPM 0014. Kurs zur funktinellen Bildgebung he general linear mdel and Statistical Parametric Mapping I: Intrductin t the GLM Alea Mrcm and Stefan Kiebel, Rik Hensn, Andrew Hlmes & JB Pline Intrductin
More information