Challenge No. 2: Forecasting at Packware Co.

Rosy Rosenbach left the conference room at Packware Corporation (PC) with some concerns. Her divisional manager had informed her that her marketing team was responsible for improving supply chain performance at PC, as the company has been unable to effectively meet customer demand over the past few years. Rosy had little contact with PCs customers (retailers) and pondered how she would add value to this process. She was told by her division manager that the teams first task was to establish a collaborative forecast using data from both PC and its customers. This forecast would serve as the basis for improving the companys performance, as managers could use this more accurate forecast for their production planning. This will also result in a better delivery performance.

PC Process

PC turns polystyrene resin into recyclable containers for the food industry. Polystyrene is purchased as a commodity in the form of resin pellets. The resin is unloaded from bulk overland trailers into storage silos. Making the food containers involves two processes. First, resin is conveyed to an extruder, which converts it into polystyrene sheet wound into rolls. The plastic comes in two forms namely clear and black. Second, the rolls are passed through thermoforming presses, which transform the sheet into containers. This process is shown in Fig. 1.

Figure 1: Manufacturing process at PC

Over the past 5 years, the plastic packaging business has grown steadily. Demand for containers made from clear plastic comes from grocery stores and restaurants. Caterers and grocery stores also use black plastic containers as packaging and serving trays. Demand for clear plastic containers peaks in the summer months, whereas demand for black plastic containers peaks in the fall.

Capacity on the extruders is not sufficient to cover demand for sheets during the peak seasons. As a result, the plant is forced to build inventory of each type of sheet in anticipation of future demand. The accompanying Excel template Packware Co. Template.xlsx contains historical quarterly demand for each of the two types of containers (clear and black).

Forecasting

As a first step, the marketing team needs to forecast quarterly demand for each of the two types of containers for the years 2020 to 2022. Based on historical trends, demand is expected to continue to grow until 2022, after which it is likely to plateau. Rosy must (a) select the appropriate forecasting method, (b) give the corresponding demand forecasted values for 2020-2022 and (c) provide an estimate of the possible forecast error.

Instructions

Use the accompanying Excel template Packware Co. Template.xlsx to assist you in answering questions (a), (b) and (c).

As a first step make a graph of the corresponding time series, namely one for clear plastic containers and one for black plastic containers. What can you conclude from these graphs alone? Tip: Adjust a linear or polynomial curve to the time series.

Based on the graphs analysis select the most appropriate forecasting method. Justify your choice.

Using the demand data provided for both types of containers, produce forecast estimates for each quarter from 2020 to 2022.

Estimate forecast error using the MAPE measure. For this, you should proceed as follows (ex-ante procedure): Repeat step 4, but instead of using the complete time series from 2015 to 2019 to estimate the model parameters, use only the data for the years 2015-2018. Then using this new model produce new demand forecasts for each quarter of 2019. Finally use the real data for 2019 (original values) and compare these values with your forecasted values to calculate the MAPE.

Include your notes and conclusions directly in the Excel file, together with the numerical analysis.

			Black Plastic	Clear Plastic
	Year	Quarter	Demand ('000 lb)	Demand ('000 lb)
	2015	I	2,260	3,205
		II	1,738	7,655
		III	2,415	4,421
		IV	7,275	2,383
	2016	I	3,510	3,654
		II	2,145	8,687
		III	3,463	5,692
		IV	7,052	1,953
	2017	I	4,120	4,743
		II	2,770	13,675
		III	2,550	6,642
		IV	8,251	2,736
	2018	I	5,493	3,488
		II	4,380	13,185
		III	4,315	5,442
		IV	12,037	3,489
	2019	I	5,645	7,723
		II	3,698	16,590
		III	4,842	8,238
		IV	13,096	3,314
	2020	I
		II
		III
		IV
	2021	I
		II
		III
		IV
	2022	I
		II
		III
		IV