MIS 665 Full Course DiscussionsMIS 665 Topic 1 DQ 1Forecasting techniques rely on the adage that history repeats itself. Many times, though, it has been noted that there is no guarantee that historical patterns will repeat and, even if they do, it can be difficult or impossible to predict when a pattern will repeat itself. Provide two-time series examples that seemed stable and predictable until there was a significant change to the pattern. Was there a way to predict the pattern change? Explain.

MIS 665 Topic 1 DQ 2
Technically, once a time series model is built, any future value can be forecasted. For example, assume you built a model that forecasts monthly sales of a product given the last 3 months of sales. Using the model, you forecasted monthly sales for the next 6 months, and the model provided very accurate predicted sales.

Your manager wants to use your model to predict sales for the next 5 years. What are some problems that could occur with extending the forecast horizon out that far? How would this affect your confidence in the forecasted values for a year? Five years? Explain.

MIS 665 Topic 2 DQ 1
Consider the following scenario and address the questions that follow.

Suppose your company wanted to determine the number of sales of a new SUV model, called Lightning. The sales estimate would be based on the overall demand of various SUV model types. Overall demand is assumed to be normally distributed with a mean of 3 million units and a standard deviation of 500,000 units. The share of demand that Lightning will take is assumed to be 4%. After running 1,000 simulated scenarios, a 95% confidence interval was constructed for the expected sales of Lightning units sold with limits of 93,048 and 146,964.

If 1,000 new simulated scenarios were run, would you get the exact result? Explain why.
Would the results be more stable if you ran 2,000 runs? Explain why.
Is there a number of simulations that can be run so that the results do not change if you re-ran the simulations? Explain.
MIS 665 Topic 2 DQ 2
Reconsider the scenario presented in DQ 1 and address the questions that follow.

Suppose your company wanted to determine the number of sales of a new SUV model, called Lightning. The sales estimate would be based on the overall demand of various SUV model types. Overall demand is assumed to be normally distributed with a mean of 3 million units and a standard deviation of 500,000 units. The share of demand that Lightning will take is assumed to be 4%. After running 1,000 simulated scenarios, a 95% confidence interval was constructed for the expected sales of Lightning units sold with limits of 93,048 and 146,964.

If a mean of 6 million units was used in the simulation, how would the confidence interval change? Explain.
How would the confidence interval change if a standard deviation of 250,000 was used? Explain.
MIS 665 Topic 3 DQ 1
Before computers were widespread, almost all risk analysis was done without simulation. Therefore, only a handful of scenarios could be formulated to understand the risk of a decision. Typically, a best-case and worst-case scenario were determined and decisions were based on these two scenarios. What are some of the drawbacks of this decision-making approach? Specifically, how does the capability to summarize 1,000s of simulated scenarios improve the approach?