Abb Electric - Marketing Analytics

Using the descriptor data sheet, I calculated the total marketing cost for each customer and then the likely profit using the equation given. After sorting the profit in descending order, I selected the top customers until the total marketing cost reached a million dollars. This gives us a maximum profit potential of $5,439,500. ABB needs to target the following customers – 35,43,44,66,32,11,37,42,21,57,58,54,3,50,69,13,61,41,45,87.

I ran the multinomial-logit model on the survey data. From the diagnosis sheet, I obtained a hit rate of 87.5%. Although the hit rate is pretty high and shows that there is a fair amount of convergence between predicted and observed values, the opportunity cost of ABB is 27.78% which is weaker than the hit rate. Hence the model fit can be made better by further surveys.

Price, energy loss, warranty, ease of install, problem solver, quality are all positively correlated. Maintenance and spare parts are not statistically significant. For every unit increase in price, probability of purchasing ABB increases by 697.4%. For every unit increase in energy loss, probability increases by 1113.2%. For every unit increase in warranty, probability of buying increases by 200.1%. For every unit increase in ease of install, probability increases by 63.3%. For every increase in problem solver, probability increases by 533.7% and for every increase of quality, probability increases by 1090%. Customers perceive quality and energy efficiency to be the primary drivers as their buying choice. Price and sales staff follow suit. Warranty is a good bonus and ease of install hardly makes a lot of difference.

Every 1% increase in price of ABB, probability of ABB purchase increases by 3.82% and probability of purchase of GE, Westinghouse and Edison fall by 1.06%, .83% and .52%. According to table B, ABB is very price sensitive. Increase of 1% in price of the other brands increases purchase probability by 1.75%, 1.71% and 1.75% in each of GE, Westinghouse...