IFC$/$PREWORK#

Scenario

You have been given a task to create a demand forecast for the second year of sales of a premium outdoor grill. Accurate forecasts are important for many reasons, including for the company to ensure they have the materials they need to create the products required in a certain period of time. Your objective is to minimize the forecast error, which will be measured using the Mean Absolute Percentage Error $($MAPE$)$ with a goal of being below $25\%.$

You have historical monthly sales data for the past year and access to software that provides forecasts based on five different forecasting techniques $($Na$$ve$,3-$Month Moving Average, Exponential Smoothing for $\mathrm{.}2,$ Exponential Smooth for $\mathrm{.}5,$ and Seasonal$)$ to help determine the best forecast for that particular month. Based on the given data, you will identify trend's and patterns to create a more accurate forecast.

$$pproach

Consider the previous month's forecast to identify which technique is most effective. Use that to forecast the next month.

Remember to select the forecasting technique that produces the forecast error nearest to zero. For example:

a$.$ Na$$ve Forecast is $230$ and the Forecast Error is $-15.$

b$.3-$Month Moving Forecast is $290$ and the Forecast Error is $-75.$

c$.$ Exponential Smoothing Forecalit for $.2$ is $308$ and the Forecast Error is $-93.$

d$.$ Exponential Smoothing Forecast for $\mathrm{.}5$ is $279$ and the Forecast Error is $-64.$

e$.$ Seasonal Forecast is $297$ and the Forecast Error is $-82.$

The forecast for the next month would be $230$ as the Na$$ve Forecast had the Forecast Error closest to zero with a $-15.$ This forecasting technique was the best performing technique for that month. You do not need to do any external analysis$-$the forecast error for each strategy is already calculated for you in the tables below.Activity $1$: Year $2$ Forecast

$\backslash$table$[[$Forecast next period,Year $2,$MAPE$\%,$Average :MAPE$],[$JAN$,1,2,,],[$FEB$,,,],[$MAR$,,,],[$APR$,,,4],[$MAY$,,,],[$JUN$,,,],[$JUL$,,,],[$AUG$,,,],[$SEPT$,,,],[$OCT$,0^{},,],[$NOV$,,,],[$DEC$,,,]]$

$\backslash$table$[[$Actual Demand,$],[$Month$,$Year $1,$Year $2,$Seasonal Index$],[$JAN$,82,,0\mathrm{.}954],[$FEB$,87,0\mathrm{.}848,],[$MAR$,82,0\mathrm{.}901,],[$APR$,112,1\mathrm{.}033,],[$MAY$,117,1\mathrm{.}298,],[$JUN$,123,1\mathrm{.}219,],[$JUL$,102,1\mathrm{.}139,],[$AUG$,123,,1\mathrm{.}113],[$SEPT$,87,,1\mathrm{.}033],[$OCT$,77,,0\mathrm{.}848],[$NOV$,87,,0\mathrm{.}848],[$DEC$,77,,0\mathrm{.}768]]$

Activity $2$: Forecast Technique Analysis

Forecasting technique that best fits the data: Select