Critical Thinking: Benefits of Using a Formalized System to Forecasting of New Products

Forecasting is a technique that uses past data and information to model future events and outcomes. There are a number of benefits that come with formalized system of forecasting that M&L Manufacturing company can take advantage of. One of the benefits is that it would help the management of the company improve production planning and inventory management, (Stevenson, 2018). This would be important in ensuring that the company has a reliable estimate of the expected demand for the two products and subsequently properly plan for optimum production levels. This further would smoothen the production and supply of the two products in the market in a manner that caters for the prevailing demand. Instances of understocking and overstocking would also be avoided helping the company ensure that it does not miss sales opportunities while at the same time saving on the heavy storage costs that occur when the production process is uneven, (Pandey et al., 2014).

Formalized forecasting procedure is beneficial in that it helps reduce risk and uncertainty that is associated with being unsure of how the demand for the products is likely to behave. It helps the managers be able to extrapolate and predict the trend taken by demand way into the future, (Foltz, 2012). With this tool therefore, the managers of the company can have a gist as to how demand will look like in the future and try to come up with strategies to ensure that sales do not decline over time.

It is equally beneficial in that it helps the company establish what products are in high demand in the market and provide them in a manner that customers want. This translates into increased customer satisfaction and loyalty making demand and sales more smooth. Profitability of the company further increases due to increased sales, (Coke & Helo, 2016).

Forecasting, especially using historical prices, is beneficial because it helps the company form an impression of the trend of the sales in the past. The managers are able to see instances when sales declined and try to find out reasons that could have led to such decline, (Randhear & Al-Aali, 2015). This becomes helpful in policy and strategy creation in a bid to ensure that such instances do not recur in the future. It also equally helps the management form an opinion regarding the strength of demand for products and make pricing adjustments for even improved cash flows for the company, (Terry & Xiao, 2009).

Forecasting can be beneficial in helping a company identify new business lines. Forecasting, especially when based on customer perceptions regarding the existing products and new products that they would like to have in the market, can be insightful in helping a business create new business lines which translate to increased sales, cash flows and profitability.

Forecasting method and forecasts for the next four weeks

In light of the numerous benefits of forecasting, M&L Manufacturing would like to forecast demand for Products 1 and 2 for the next four weeks. To achieve this objective, the method of ordinary least squares using simple linear regression will be used for each of the two products. This method is chosen in forecasting demand for the two products because it minimizes the sum of squared residuals in a regression model, resulting in efficient and reliable estimates that can be used in forecasting, (Srinivasan, 2012). Two regression models will be created. They will then be used to estimate the demand for each product over the next four weeks. I choose this technique because it is appropriate in analyzing and fitting the relationship between two or more variables in a line of best fit such that the effect of the independent variable on the dependent variable can be modeled in a linear form and then used to estimate outcomes of the dependent variable in future. It is also appropriate because it yield best linear unbiased estimators that help measure the effect of the independent variable, for instance time, on the dependent variable, (Fildes et al., 2008). For this case, product demand will be the dependent variable while time in terms of weeks will be the independent variable. The modeling is done as shown below:

Demand for Product 1( the data in page 132 of the text is used)

y=1039, x=105, x2=1015, xy=8579, y/n=74.21428571, x/n=7.5, n=14 and x is time in weeks while y is demand for product 1. A regression model of the following form can be formed:

Y=a+bx where y and x are as defined above and a and b are the intercept and slope of the line of best fit respectively. They measure relationship between time and demand for product 1.

a =(y/n)-b(x/n)= 74.21428571-3.457142857(7.5)=48.28571428

b=(xy-nx/ny/n)/( x2-n(x/n)2)=3.457142857

hence the model for product 1 is: y=48.2857+3.4571x (1)

Predicted values for the next four weeks will be obtained when x assumes values of 15, 16, 17 and 18. These values are plugged into equation 1 where there is x. The values are rounded up to the nearest whole number.

The same procedure is repeated for product 2 and the following values obtained:

a =(y/n)-b(x/n)= 42.7857-0.362643956(7.5)=40.0659

b=(xy-nx/ny/n)/( x2-n(x/n)2)=0.362643956

hence the model for product 1 is: y=40.0659+0.3626x

Weekly forecasts for the next four weeks

Week Product 1 Product 2

15 100 46

16 104 46

17 107 46

18 111 47

References

Coker, J., Helo, P. (2016). Demand-supply balancing in manufacturing operations, Benchmarking, 23(3), 564-583.

Fildes, R., Nokolopoulos, S.F., Syntetos, A.A., Crone, S.F. (2008). Forecasting and Operational Research: A Review, Journal of Operational Research Society, 59(9), 1150-1172.

Foltz, B. (2012). Operations management 101: Measuring forecast error [Video file]. Retrieved from https://www.youtube.com/watch?v=m0Wbj0-yJ5c.

Pandey, P., Kumar, S., Shrivastava, S. (2014). A unified strategy for forecasting of a new product, Decision, 41(4), 411-424.

Randheer, K., Al-Aali, A. (2015). What, who, how and where: Retailing industry in Saudi Arabia, Journal of Competitiveness Studies, 23(3), 54-69.

Srinivasan, G. (2012). Mod-02lec-02 Forecasting-Time series models-simple exponential smoothing[Video file]. Retrieved from https://www.youtube.com/watch?v=k9dhcflyOFcStevenson, W. (20180. Operations management (13 ed.) New York, NY: McGraw-Hill Irwin. ISBN-13:9781259667473.

Terry, A.T., Xiao, W. (2009). Incentives fore Retailer Forecasting: Rebates vs. Returns, Management Science, 55(10), 1654-1669.