Time Series Forecasting Principles with Amazon Forecast

Time Series Forecasting Principles with Amazon Forecast

Technical Guide

First Published February 2020 Updated September 1, 2021

This version has been archived.

For the latest version of this document, visit:

time-series-forecasting-principles-with-amazonforecast/time-series-forecasting-principles-withamazon-forecast.html

Notices

Customers are responsible for making their own independent assessment of the information in this document. This document: (a) is for informational purposes only, (b) represents current AWS product offerings and practices, which are subject to change without notice, and (c) does not create any commitments or assurances from AWS and its affiliates, suppliers or licensors. AWS products or services are provided "as is" without warranties, representations, or conditions of any kind, whether expressed or implied. The responsibilities and liabilities of AWS to its customers are controlled by AWS agreements, and this document is not part of, nor does it modify, any agreement between AWS and its customers.

? 2021 Amazon Web Services, Inc. or its affiliates. All rights reserved.

This version has been archived.

For the latest version of this document, visit:

time-series-forecasting-principles-with-amazonforecast/time-series-forecasting-principles-withamazon-forecast.html

Contents

About this guide...................................................................................................................5 Overview ..............................................................................................................................6 About forecasting.................................................................................................................6

Forecasting system ..........................................................................................................7 Where do forecasting problems occur?...........................................................................7 Considerations before attempting to solve a forecasting problem .................................8 Case study: Retail demand forecasting problem for an e-commerce business ................9 Step 1: Collect and aggregate data ..................................................................................11 Example .......................................................................................................................... 13 Step 2. Prepare data .........................................................................................................14 How to handle missing data...........................................................................................14 Example 1.......................................................................................................................15 Example 2.......................................................................................................................17 Concepts of featurization and related time series.........................................................17

Example 3...................T...h...i.s....v..e...r..s..i..o...n....h...a...s...b...e...e..n.....a..r..c...h...i.v...e...d.................................18

Step 3: Create a predictor .................................................................................................19 Step 4: Evaluate predictors ...............................................................................................21

Backtesting .....F...o...r...t..h...e....l.a...t.e...s..t...v...e..r..s..i..o..n.....o...f...t..h..i..s...d...o...c..u...m....e...n...t..,..v...i.s..i.t..:..............21

Prediction quantiles and accuracy metrics ....................................................................23 Weighted Quantile Loss (wQL) ................................................................................. 23

Weighted Atbimsoelu-tseePreiercse-nftoargeecEarsrtoirn(gW-ApPrEin) c..i..p..l..e..s..-..w...i.t..h...-.a...m....a..z..o...n..-................. 24 Root MeanfSoqreuacraesEt/rrtoimr (ReM-sSeEri)e..s..-..f.o...r..e..c..a..s..t..i.n...g..-..p...r..i.n..c...i.p..l..e..s..-..w...i..t.h...-................ 24 Problems with WAPE and RMaSmE .a..z..o...n..-..f..o..r..e..c..a...s..t....h..t..m....l............................................25

Step 5: Generate and use forecasts for decision making ................................................26 Probabilistic forecasts ....................................................................................................26

Visualization ...................................................................................................................27 Summary of forecasting workflow and APIs .....................................................................28

Using Amazon Forecast for common scenarios ...........................................................29 Implementing Forecast into production .........................................................................30 Conclusion .........................................................................................................................31 Contributors .......................................................................................................................32 Further reading ..................................................................................................................32 Appendix A: FAQs .............................................................................................................33 Appendix B: References....................................................................................................36 Document versions............................................................................................................37

This version has been archived.

For the latest version of this document, visit:

time-series-forecasting-principles-with-amazonforecast/time-series-forecasting-principles-withamazon-forecast.html

About this guide

Companies today use everything from simple spreadsheets to complex financial planning software in a bid to accurately forecast future business outcomes such as product demand, resource needs, and financial performance. This paper introduces forecasting, its terminology, challenges, and use cases. This document uses a case study to reinforce forecasting concepts, forecasting steps, and references how Amazon Forecast can help solve the many practical challenges in real-world forecasting problems.

This version has been archived.

For the latest version of this document, visit:

time-series-forecasting-principles-with-amazonforecast/time-series-forecasting-principles-withamazon-forecast.html

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download