Can we reliably forecast individual 3G usage data? An analysis using mathematical simulation of time series algorithms Cosmo Zheng.

Slides:



Advertisements
Similar presentations
Module 4. Forecasting MGS3100.
Advertisements

Forecasting.
Forecasting Models With Linear Trend. Linear Trend Model If a modeled is hypothesized that has only linear trend and random effects, it will be of the.
Forecasting Demand ISQA 511 Dr. Mellie Pullman.
Forecasting 5 June Introduction What: Forecasting Techniques Where: Determine Trends Why: Make better decisions.
Qualitative Forecasting Methods
Analyzing and Forecasting Time Series Data
Chapter 3 Forecasting McGraw-Hill/Irwin
1 Time Series Analysis Thanks to Kay Smith for making these slides available to me!
Chapter 13 Forecasting.
Principles of Supply Chain Management: A Balanced Approach
Forecasting & Time Series Minggu 6. Learning Objectives Understand the three categories of forecasting techniques available. Become aware of the four.
Demand Management and Forecasting. Types of Forecasts Qualitative Time Series Causal Relationships Simulation.
Part II – TIME SERIES ANALYSIS C2 Simple Time Series Methods & Moving Averages © Angel A. Juan & Carles Serrat - UPC 2007/2008.
Forecasting McGraw-Hill/Irwin Copyright © 2012 by The McGraw-Hill Companies, Inc. All rights reserved.
Copyright 2013 John Wiley & Sons, Inc. Chapter 8 Supplement Forecasting.
Chapter 11 Solved Problems 1. Exhibit 11.2 Example Linear and Nonlinear Trend Patterns 2.
MOVING AVERAGES AND EXPONENTIAL SMOOTHING. Forecasting methods: –Averaging methods. Equally weighted observations –Exponential Smoothing methods. Unequal.
CHAPTER 18 Models for Time Series and Forecasting
© 2003 Prentice-Hall, Inc.Chap 12-1 Business Statistics: A First Course (3 rd Edition) Chapter 12 Time-Series Forecasting.
Homework Solution Weighted Averages - Exponential Smoothing - Trend Cool-Man Air Conditioners Manual ManualComputer-Based TM MGMT E-5070 Part B.
G. Peter Zhang Neurocomputing 50 (2003) 159–175 link Time series forecasting using a hybrid ARIMA and neural network model Presented by Trent Goughnour.
Winter’s Exponential smoothing
Samuel H. Huang, Winter 2012 Basic Concepts and Constant Process Overview of demand forecasting Constant process –Average and moving average method –Exponential.
Time Series “The Art of Forecasting”. What Is Forecasting? Process of predicting a future event Underlying basis of all business decisions –Production.
Introduction to Forecasting COB 291 Spring Forecasting 4 A forecast is an estimate of future demand 4 Forecasts contain error 4 Forecasts can be.
Forecasting Copyright © 2015 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written consent of McGraw-Hill.
Copyright © 2012 Pearson Education, Inc. All rights reserved. Chapter 10 Introduction to Time Series Modeling and Forecasting.
1 What Is Forecasting? Sales will be $200 Million!
Forecasting MD707 Operations Management Professor Joy Field.
DSc 3120 Generalized Modeling Techniques with Applications Part II. Forecasting.
Time-Series Forecasting Learning Objectives 1.Describe What Forecasting Is 2. Forecasting Methods 3.Explain Time Series & Components 4.Smooth a Data.
Time series data: each case represents a point in time. Each cell gives a value for each variable for each time period. Stationarity: Data are stationary.
Forecasting Models Decomposition and Exponential Smoothing.
Definition of Time Series: An ordered sequence of values of a variable at equally spaced time intervals. The variable shall be time dependent.
CHAPTER 5 DEMAND FORECASTING
Simple Exponential Smoothing The forecast value is a weighted average of all the available previous values The weights decline geometrically Gives more.
Time-Series Forecasting Overview Moving Averages Exponential Smoothing Seasonality.
Demand Management and Forecasting Module IV. Two Approaches in Demand Management Active approach to influence demand Passive approach to respond to changing.
© 1999 Prentice-Hall, Inc. Chap Chapter Topics Component Factors of the Time-Series Model Smoothing of Data Series  Moving Averages  Exponential.
Welcome to MM305 Unit 5 Seminar Prof Greg Forecasting.
Time Series Analysis and Forecasting. Introduction to Time Series Analysis A time-series is a set of observations on a quantitative variable collected.
© Wallace J. Hopp, Mark L. Spearman, 1996, Forecasting The future is made of the same stuff as the present. – Simone.
Forecasting Demand. Forecasting Methods Qualitative – Judgmental, Executive Opinion - Internal Opinions - Delphi Method - Surveys Quantitative - Causal,
Economics 173 Business Statistics Lecture 25 © Fall 2001, Professor J. Petry
Time-Series Forecast Models  A time series is a sequence of evenly time-spaced data points, such as daily shipments, weekly sales, or quarterly earnings.
1 1 Chapter 6 Forecasting n Quantitative Approaches to Forecasting n The Components of a Time Series n Measures of Forecast Accuracy n Using Smoothing.
CHAPTER 12 FORECASTING. THE CONCEPTS A prediction of future events used for planning purpose Supply chain success, resources planning, scheduling, capacity.
Forecasts and Projections “A trend is a trend is a trend, But the question is, will it bend? Will it alter its course Through some unforeseen force And.
Assignable variation Deviations with a specific cause or source. forecast bias or assignable variation or MSE? Click here for Hint.
3-1Forecasting Weighted Moving Average Formula w t = weight given to time period “t” occurrence (weights must add to one) The formula for the moving average.
1 Autocorrelation in Time Series data KNN Ch. 12 (pp )
Time Series Forecasting Trends and Seasons and Time Series Models PBS Chapters 13.1 and 13.2 © 2009 W.H. Freeman and Company.
Predicting Future. Two Approaches to Predition n Extrapolation: Use past experiences for predicting future. One looks for patterns over time. n Predictive.
Welcome to MM305 Unit 5 Seminar Forecasting. What is forecasting? An attempt to predict the future using data. Generally an 8-step process 1.Why are you.
Forecasting Purpose is to forecast, not to explain the historical pattern Models for forecasting may not make sense as a description for ”physical” behaviour.
Time Series And Business Forecasting
Forecasting techniques
Forecasting Approaches to Forecasting:
Chapter 17 Forecasting Demand for Services
Time Series Forecasts Trend - long-term upward or downward movement in data. Seasonality - short-term fairly regular variations in data related to factors.
Forecasting Chapter 11.
“The Art of Forecasting”
Fall, 2017 EMBA 512 Demand Forecasting
Forecasting Elements of good forecast Accurate Timely Reliable
Chapter 8 Supplement Forecasting.
Forecasting - Introduction
OUTLINE Questions? Quiz Go over homework Next homework Forecasting.
MGS 8110 Applied Regression/Forecasting
Exponential Smoothing
Presentation transcript:

Can we reliably forecast individual 3G usage data? An analysis using mathematical simulation of time series algorithms Cosmo Zheng

Background Fluctuations in daily demand for bandwidth make ordinary usage pricing inefficient Solution: Time- dependent pricing to persuade users to defer usage

Our Problem Users must be informed of expected future prices, to assess the costs of deferring usage We need a reliable way to predict future usage based on past data nology.html

The Algorithms Nonlinear regression – generate a fitted function of the form D + A*sin(2πt/24) + B*sin(2πt/12) + C*sin(2πt/6) Use fitted function to extrapolate

Algorithms (cont.) Time series decomposition – isolate trend, seasonal, and residual components Extend trend and seasonal components into the future

Algorithms (cont.) Exponential smoothing – generate {S t } based on a weighted average of previous data Simplest form is S 1 = X 0, S t = αX t-1 + (1-α)S t-1 for t>1, where α is a smoothing factor

The Data Use simulated datasets, representing usage each hour over 5 days {X t } for 1 <= t <= 120 First 4 days are historical data (training set), 5 th day is the test set

Algorithm 1: Regression

Regression (cont.) R 2 = 0.424

Algorithm 2: Decomposition

Decomposition (cont.) R 2 = 0.693

Algorithm 3: Smoothing

Smoothing (cont.) R 2 = 0.516

Additional Trials Trial #RegressionDecompositionSmoothing Average Trial #RegressionDecompositionSmoothing Average Sum of absolute error R2R2

Conclusions Time series decomposition provided most accurate prediction of future usage, followed by exponential smoothing, then regression Possible explanation: usage pattern is strongly cyclic; repeats itself on a daily basis Suggestion: investigate further into better means of isolating seasonal data; some more sophisticated algorithms exist (ARIMA, stochastic volatility models).