The cell phone industry as booming at a tremendous rate and with every passing day new developments can be seen. No contemporary cultural artifact embodies the genius and the disruptive excess of capitalism as clearly as the cell phone. Ubiquitous in most developed societies in Europe, the Americas, and Asia, the cell phone has become a laboratory; some would say an asylum, for testing the limits of technological convergence.
Less a telephone today than a multi-purpose computer, cell phones are game consoles, still cameras, email systems, text messengers, carriers of entertainment and business data, nodes of commerce. Particular age cohorts and subcultures have begun to appropriate cell phones for idiosyncratic uses that help to define their niche or social identity. By taking a look at the trend in sales of the past 36 months I was able to apply the least square regression method and come up with the following equation which would allow me to predict the number of cases sold in the upcoming 6 or 12 months (Heizer & Render 2011). This will allow Digital Cell Phone Inc. to predict how many cases to produces every month based on the trends in sales of each month. Regression analysis can be very useful for any company as it helps you statistically put two variables, a dependent and an independent variable against each other and then shows us its result. A linear regression line can also be drawn using the values given in the table below. The slope or gradient of this line would always be 1.42 and the Y- intercept would always be 1.42. The independent variable is X whereas the dependent variable is Y whose outcome is dependent on X as shown in the derived information given below. (Heizer & Render 2011)
Y=600 + 1.42 X
Given our assumption of a straight line relationship between cell phone sales and the month, we have an indication of that slope of that relationship. Since the sales of cell phones are varying from month to month, the exact amount of cell phones to be produced each month cannot be calculated. However, the table given above gives us the predicted sales based on a regression analysis for the next 12 months.
When we add seasonality to this analysis using the multiplicative seasoning model, we are able to find the predicted demand for cell phones each month. We can see the trend and seasonality for cell phones (Heizer & Render 2011). Adding seasonality to the equation lets us know the average amount of sales that will take place every month. The variations in the number of sales each month can have an effect on profitability and the information provided by the seasonality regression analysis can also be used to reduce output and cost during seasons of relatively lesser sales and simultaneously it could also be used to increase the output during peak seasons. This would help the CEO in making seasonal investments (Heizer & Render 2011). A seasonal investment by definition is profitable more than 50% of the time. If the frequency of profitable trades is 50% and the frequency of unprofitable trades is 50%, results are random. Confidence in seasonal trade increases with the frequency of profitable trades.
Reference
Heizer, J., & Render, B. 2011. Operation management (10th edn.). New Jersey: Pearson Education.