Product X is due to launch in 6 months time and I am looking for a method to estimate what the sales of this product could likely be in 3 years time.

Product X belongs to a category of products for which I have daily historical sales going back 5 years, in this category there are 4 other products [A,B,C,D] which are similar in attributes to X but X is deemed to be a superior product.

I've read about Bass diffusion models to estimate new product sales but I am wondering if I can use the sales data from the other products in the category to estimate the sales of X. Can I estimate the Bass model parameters for products A,B,C & D and take the average of these?

Right now our product experts use a finger in the air approach (65% of product B's sales) to estimate the sales of X but I am looking to apply a bit more analytical rigor in my approach. It doesn't have to be a deep learning model but just something sufficiently more robust than taking a guess of the expected sales.

I would be very grateful if any of the boffins here could provide some direction please

  • $\begingroup$ You need to conduct a demand study aka market research by speaking to customers. Then calibrate the expert opinion and apply to analogs (4 other products). There are several criteria one can use to choose analogs, order of entry (is your product 5th to market), is your product superior to existing product etc., no need for statistical models here. All you need is good analog based forecasts combined with expert(market research). $\endgroup$ – forecaster Feb 19 at 16:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.