Oregon Chain Saw Company Case Study

Case: Oregon Chain Saw

9/14/2018

Executive Summary

Oregon Chain Saw is a company that produces chain-saws for various markets. They purchase engines for these chain saws from outside suppliers, but produce all other parts of the saw in its Portland factory. The manager of this factory, Lee Spencer, would like to schedule next year’s production based on a forecast of demands over this period.

According to data derived from the initial measurements, the demand for 17-inch chain saws is a lot more regular and constantly increasing, whereas that for the 21-inch chain saws is seasonal and sporadic, as displayed in Exhibit 1.

I recommend devoting more workers to the 17-inch saws- 77% of the workforce, according to calculations in Exhibit 5, because the demand values for these saws is significantly higher than for the 21-inch saws. 21-inch chains should utilize 23% of the workforce, according to Exhibit 5. The company should prepare to make about 16,000 17-inch chains a year, according to forecasted data in Exhibit 2, every year. In addition to those preparations, having supplies and the workforce necessary to make between 6000-6432 21-inch chains in Year 5 would also benefit the company(Exhibit 3). This, in turn, will increase productivity and profits for the company, as well as make better use of resources in production.

Case Assignments:

1. For the replacement parts market of the 17-inch chains, based on its demands over last four years, suggest a method to forecast its monthly demands for the next year.

1). Display graphically the demand pattern of the past four years.

The four year actual monthly demands and individual year monthly demands are plotted below:

[pic 1]

[pic 2]

2). Determine and rationalize your method of forecasting.

From the above graphic plots of the monthly demand of 17-replacement, clearly, there is a trend and looks linear in general.  LR will be appropriate to forecast for the 5th year.

3). Show the forecasting result for the next year and include MAD and tracking signal for the last four years.

The complete forecast by using LR is shown in Exhibit 1.  The 5th year forecast are list below:

[pic 3]

The graphs for the five year forecast, MAD and TS are shown below:

[pic 4]

[pic 5]

[pic 6]

The complete forecast by using LR is shown in Exhibit 1(all data) and Exhibit 2(17 data).  The 5th year forecasts are listed below:

In particular, in the end of 4th year: MAD = 240.0651; TS = 0.

1. For the new product production of the 17-inch chains, based on its demands over the last four years, suggest a method to forecast its monthly demands for the next year.

1). Display graphically the demand pattern of the past four years.

[pic 7]

2). Determine and rationalize your method of forecasting.

Seems to be seasonal pattern trend, because demand is non-linear but there is a pattern to the data. Seasonal pattern trend forecasting should be appropriate.

3). Show the forecasting result for the next year and include MAD and tracking signal for the last four years.

The complete forecast by using Seasonal Pattern Trend is shown in Exhibit 1(all data) and Exhibit 2(17 data).  The 5th year forecast are list below:

[pic 8]

[pic 9]

[pic 10]

[pic 11]

In particular, in the end of 4th year: MAD = 1166.5122; TS = 0.

1. For the demand of 17-inch chains, add the forecast results from (1) and (2) to obtain the monthly demands for the next year.  Alternatively but not recommended, you could use the total demand of 17-inch chains for the last four years to determine the pattern and method to forecast its monthly total demands for the next year.

The full calculations are displayed in Exhibit 1(all data) and Exhibit 4(sums). The results of the calculations are displayed below.

[pic 12]

[pic 13]

1. For the replacement parts market of the 21-inch chains, based on its demands over the last four years, suggest a method to forecast its monthly demands for the next year.

1). Display graphically the demand pattern of the past four years.

[pic 14]

[pic 15]

2). Determine and rationalize your method of forecasting.

By taking a look at the graphs above, clearly the data is non-linear. Forecasting Method I would suggest is Seasonal Demand.

3). Show the forecasting result for the next year and include MAD and tracking signal for the last four years.