Package TSprediction



Similar documents
Time series Forecasting using Holt-Winters Exponential Smoothing

MGT 267 PROJECT. Forecasting the United States Retail Sales of the Pharmacies and Drug Stores. Done by: Shunwei Wang & Mohammad Zainal

Indian School of Business Forecasting Sales for Dairy Products

Forecasting Analytics. Group members: - Arpita - Kapil - Kaushik - Ridhima - Ushhan

Demand Forecasting LEARNING OBJECTIVES IEEM Understand commonly used forecasting techniques. 2. Learn to evaluate forecasts

Cross Validation. Dr. Thomas Jensen Expedia.com

A Comparative Study of the Pickup Method and its Variations Using a Simulated Hotel Reservation Data

Forecasting in supply chains

Causal Leading Indicators Detection for Demand Forecasting

Package empiricalfdr.deseq2

Promotional Forecast Demonstration

FOCUS FORECASTING IN SUPPLY CHAIN: THE CASE STUDY OF FAST MOVING CONSUMER GOODS COMPANY IN SERBIA

Module 6: Introduction to Time Series Forecasting

Forecasting sales and intervention analysis of durable products in the Greek market. Empirical evidence from the new car retail sector.

Objectives of Chapters 7,8

IBM SPSS Forecasting 22

Demand Forecasting to Increase Profits on Perishable Items

A Regression Approach for Forecasting Vendor Revenue in Telecommunication Industries

2) The three categories of forecasting models are time series, quantitative, and qualitative. 2)

Product Documentation SAP Business ByDesign Supply Chain Planning and Control

MICROSOFT EXCEL FORECASTING AND DATA ANALYSIS

Package CoImp. February 19, 2015

CHAPTER 11 FORECASTING AND DEMAND PLANNING

Sales and operations planning (SOP) Demand forecasting

4. Forecasting Trends: Exponential Smoothing

Forecast the monthly demand on automobiles to increase sales for automotive company

Not Your Dad s Magic Eight Ball

Outline. Role of Forecasting. Characteristics of Forecasts. Logistics and Supply Chain Management. Demand Forecasting

CB Predictor 1.6. User Manual

Week TSX Index

Baseline Forecasting With Exponential Smoothing Models

Outline: Demand Forecasting

The Operational Value of Social Media Information. Social Media and Customer Interaction

Performance Measures in Data Mining

Package EstCRM. July 13, 2015

ISSUES IN UNIVARIATE FORECASTING

2. What is the general linear model to be used to model linear trend? (Write out the model) = or

Studying Material Inventory Management for Sock Production Factory

Problem 5: Forecasting the demand for bread st June Fernando Baladrón Laura Barrigón Ángeles Garrido Alejandro González Verónica Hernández

Forecasting Geographic Data Michael Leonard and Renee Samy, SAS Institute Inc. Cary, NC, USA

Flexible Neural Trees Ensemble for Stock Index Modeling

A Study on the Comparison of Electricity Forecasting Models: Korea and China

Forecasting DISCUSSION QUESTIONS

A COMPARISON OF REGRESSION MODELS FOR FORECASTING A CUMULATIVE VARIABLE

How To Predict Web Site Visits

Package bigdata. R topics documented: February 19, 2015

Theory at a Glance (For IES, GATE, PSU)

Intermittent Demand Forecasts with Neural Networks

The Combination Forecasting Model of Auto Sales Based on Seasonal Index and RBF Neural Network

ER Volatility Forecasting using GARCH models in R

Implementation of Inventory Management System in a Furniture Company: A Real Case study

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling

Forecasting areas and production of rice in India using ARIMA model

Chapter 4: Vector Autoregressive Models

M1 in Economics and Economics and Statistics Applied multivariate Analysis - Big data analytics Worksheet 1 - Bootstrap

SINGULAR SPECTRUM ANALYSIS HYBRID FORECASTING METHODS WITH APPLICATION TO AIR TRANSPORT DEMAND

Planning Workforce Management for Bank Operation Centers with Neural Networks

Forecasting in STATA: Tools and Tricks

Time Series Analysis and Forecasting

Corresponding Author Duke University Department of Electrical and Computer Engineering Durham, North Carolina , U.S.A.

NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling


QUANTITATIVE METHODS FOR MANAGEMENT

Time-Series Forecasting and Index Numbers

CASH DEMAND FORECASTING FOR ATMS

Demand Management Where Practice Meets Theory

Forecasting methods applied to engineering management

Simple Methods and Procedures Used in Forecasting

INCREASING FORECASTING ACCURACY OF TREND DEMAND BY NON-LINEAR OPTIMIZATION OF THE SMOOTHING CONSTANT

Package SHELF. February 5, 2016

Probability Calculator

Demand Forecasting When a product is produced for a market, the demand occurs in the future. The production planning cannot be accomplished unless

BUSINESS FORECASTING

Package benford.analysis

Package MBA. February 19, Index 7. Canopy LIDAR data

Package survpresmooth

A Wavelet Based Prediction Method for Time Series

The SAS Time Series Forecasting System

2014 Forecasting Benchmark Survey. Itron, Inc High Bluff Drive, Suite 210 San Diego, CA

RF-Microwaves formulas - 1-port systems

An online dashboard in a snap

Package SCperf. February 19, 2015

Time Series Analysis with R - Part I. Walter Zucchini, Oleg Nenadić

Package tagcloud. R topics documented: July 3, 2015

Package TRADER. February 10, 2016

> plot(exp.btgpllm, main = "treed GP LLM,", proj = c(1)) > plot(exp.btgpllm, main = "treed GP LLM,", proj = c(2)) quantile diff (error)

Environment Protection Engineering APPROXIMATION OF IMISSION LEVEL AT AIR MONITORING STATIONS BY MEANS OF AUTONOMOUS NEURAL MODELS

OSKAR Example Revision: 8

An Evaluation of Chinese Economic Forecasts

Package MDM. February 19, 2015

Package png. February 20, 2015

Package sendmailr. February 20, 2015

Implementation of demand forecasting models for fuel oil - The case of the Companhia Logística de Combustíveis, S.A. -

RapidResponse. Demand Planning. Application

Transcription:

Title Time-series forecasting package Package TSprediction September 23, 2010 TSprediction is a simple package that implements prediction methods to forecast the time-series. Version 1.56 Date 2010-08-20 Author Tomasz Bartlomowicz <tomasz.bartlomowicz@ue.wroc.pl> Maintainer Tomasz Bartlomowicz <tomasz.bartlomowicz@ue.wroc.pl> License GPL (>= 2) URL www.r-project.org, http://keii.ue. Repository CRAN R topics documented: addratio........................................... 2 addwinters......................................... 2 allnaive........................................... 3 alltrend........................................... 4 chart............................................. 5 epsmoothing........................................ 6 Holt............................................. 6 MAE............................................ 7 MAPE............................................ 8 ME............................................. 9 movaverage......................................... 9 MPE............................................. 10 MSE............................................. 11 mulratio.......................................... 12 mulwinters......................................... 13 RMSE............................................ 14 Inde 15 1

2 addwinters addratio Function addratio calculates forecasts using additive ratio method Function addratio calculates forecasts using additive ratio method. Function returns vector of forecasts. addratio(, r=4, horizon=4) r horizon length of sezon number of forecasts mulratio addratio=addratio(w, 4, 8) print(addratio) addwinters Function addwinters calculates forecasts using additive Winters model Function addwinters calculates forecasts using additive Winters model. Function returns vector of forecasts. addwinters(, r=4, alfa=0, beta=0, gamma=0, typef="first", types="difference", t

allnaive 3 r alfa beta gamma typef types typec length of sezon (number of forecasts) alfa parameter beta parameter gamma parameter kind of F argument. typef should be one of two values: first or mean kind of S argument. types should be one of two values: difference or zero kind of C argument. typec should be one of two values: ratio or one Holt addwinters=addwinters(w, 4, 0.5, 0.95, 0.2) print(addwinters) allnaive Function allnaive calculates forecasts using naive methods Function allnaive calculates forecasts using naive methods. Functions returns vector of forecasts. allnaive(, model=1, c=0) model c kind of naive method c parameter

4 alltrend Holt naive1=allnaive() print(naive1) alltrend Function alltrend calculates forecasts using trend models Function alltrend calculates forecasts using trend models. Functions returns vector of forecasts. alltrend(, model=1, horizon=3) horizon model forecast s time lead (number of forecasts) kind of analytical model Holt

chart 5 trend1=alltrend() print(trend1) chart Function chart draws data and forecasts on the same plot Function chart draws data and forecasts on the same plot chart(, yy, typec="o", lwd1=2, lwd2=2, col1="dark red", col2="dark blue") yy typec lwd1 lwd2 col1 col2 vector of data vector of forecasts kind of chart forecast s time lead kind of F argument. typef should be one of two values: first or mean kind of S argument. types should be one of two values: difference or zero kind of S argument. types should be one of two values: difference or zero allnaive y=allnaive(, 1) chart(, y)

6 Holt epsmoothing Function epsmoothing calculates forecasts using eponential smoothing model Function epsmoothing calculates forecasts using eponential smoothing model. Function returns vector of forecasts. epsmoothing(, alfa=0) alfa alfa parameter Holt epsmoothing=epsmoothing(, 0.75) print(epsmoothing) Holt Function Holt calculates forecasts using Holt s model Function Holt calculates forecasts using Holt s model. Function returns vector of forecasts. Holt(, alfa=0, beta=0, horizon=3, typef="first", types="difference")

MAE 7 alfa beta horizon typef types alfa parameter beta parameter forecast s time lead kind of F argument. typef should be one of two values: first or mean kind of S argument. types should be one of two values: difference or zero allnaive holt=holt(, 0.3, 0.7, 4) print(holt) MAE Function MAE calculates mean absolute error (MAE) Function MAE calculates mean absolute error (MAE). Function returns vector of errors and value of MAE. MAE(, y) y vector of empirical data vector of forecasts

8 MAPE ME mae=mae(, y) print(mae) MAPE Function MAPE calculates mean absolute percentage error (MAPE) Function MAPE calculates mean absolute percentage error (MAPE). Function returns vector of errors and value of MAPE. MAPE(, y) y vector of empirical data vector of forecasts MPE mape=mape(, y) print(mape)

ME 9 ME Function ME calculates mean error (ME) Function ME calculates mean error (ME). Function returns vector of errors and value of ME. ME(, y) y vector of empirical data vector of forecasts MAE me=me(, y) print(me) movaverage Function movaverage calculates forecasts using moving average method Function movaverage calculates forecasts using moving average method. Function returns vector of forecasts. movaverage(, k=0)

10 MPE k parameter of smoothing Holt movaverage=movaverage(, 3) print(movaverage) MPE Function MPE calculates mean percentage error (MPE) Function MPE calculates mean percentage error (MPE). Function returns vector of errors and value of MPE. MPE(, y) y vector of empirical data vector of forecasts

MSE 11 MAPE mpe=mpe(, y) print(mpe) MSE Function MSE calculates mean squared error (MSE) Function MSE calculates mean squared error (MSE). Function returns vector of errors and value of MSE. MSE(, y) y vector of empirical data vector of forecasts MPE mse=mse(, y) print(mse)

12 mulratio mulratio Function mulratio calculates forecasts using multiplicative ratio method Function mulratio calculates forecasts using multiplicative ratio method. Function returns vector of forecasts. mulratio(, r=4, horizon=4) r horizon length of sezon number of forecasts addratio mulratio=mulratio(w, 4, 8) print(mulratio)

mulwinters 13 mulwinters Function mulwinters calculates forecasts using multiplicative Winters model Function mulwinters calculates forecasts using multiplicative Winters model. Function returns vector of forecasts. mulwinters(, r=4, alfa=0, beta=0, gamma=0, typef="first", types="difference", t r alfa beta gamma typef types typec length of sezon (number of forecasts) alfa parameter beta parameter gamma parameter kind of F argument. typef should be one of two values: first or mean kind of S argument. types should be one of two values: difference or zero kind of C argument. typec should be one of two values: ratio or one Holt mulwinters=mulwinters(w, 4, 0.5, 0.95, 0.2) print(mulwinters)

14 RMSE RMSE Function RMSE calculates root mean squared error (RMSE) Function RMSE calculates root mean squared error (RMSE). Function returns vector of errors and value of RMSE. RMSE(, y) y vector of empirical data vector of forecasts MSE rmse=rmse(, y) print(rmse)

Inde Topic multivariate addratio, 1 addwinters, 2 allnaive, 3 alltrend, 4 chart, 4 epsmoothing, 5 Holt, 6 MAE, 7 MAPE, 8 ME, 8 movaverage, 9 MPE, 10 MSE, 11 mulratio, 11 mulwinters, 12 RMSE, 13 addratio, 1, 12 addwinters, 2 allnaive, 3, 5, 7 alltrend, 4 chart, 4 epsmoothing, 5 Holt, 3, 4, 6, 6, 10, 13 MAE, 7, 9 MAPE, 8, 10 ME, 7, 8 movaverage, 9 MPE, 8, 10, 11 MSE, 11, 13 mulratio, 2, 11 mulwinters, 12 RMSE, 13 15