3.2 Articles

3.2.1 A new product growth model for consumer durables,” Management Science

The Bass Model i.e. the Bass Curve is the model for sales of new products, or more correct a generalization of the sales for a product, hence he created the model for adopters, where it has later been separated into innovators, early adopters, early majority, etc. that is then the product life cycle.

Thus the purpose of the Bass Model is to predict sales of a new product, based on questionnaires or early sales

The Bass Curve is based on the early adopters and calculates the curve based on their numbers. The model has proven that it only needs very few observations to plot when it is going to peak and at what amount. Basically the model is based on a conditional likelihood with respect to time.

In fact, it has shown to predict peak and sales amount based on research and questionnaires prior to sales

Then there are some notes on what further research that can be done and some notes on extensions to the Bass Model

3.2.2 Sales Forecasts for Existing Consumer Products

and Services: Do Purchase Intentions Contribute to Accuracy?

As we know from the Bass Model we can use consumer intentions (questionnaires about whether a person think he will buy it or not) to guestimate the total sales and when it is going to peak, but are we are able to optimize accuracy of forecasts on existing products using consumer intentions?

A previous study has shown, that intentions does not improve the model, although the data did not have available the intentions and whether the person made a purchase or not. In this study there is an improvement to the forecast when the historical data is combined with the intentions of the persons. Also they ruled out, the factor that if the data does not have historical data on intentions and sales history. Hence they experienced on their seven data set, that combining historical data and intentions improved the forecast. To be noted is that the manipulated the intentions in different ways to experiment, e.g. moving average, binary (intentions or not) and some other faucets.

3.2.3 Judgmental forecasting A review of progress over the last 25 years, International Journal of Forecasting

This is basically just more information on the judgemental forecasting where they tested different set ups, such as groups, bootsstrapping etc.

Did not read all of this, it seemed very much like HW9