Analytics-driven solutions for customer targeting and sales-force allocation

Abstract

Sales professionals need to identify new sales prospects, and sales executives need to deploy the sales force against the sales accounts with the best potential for future revenue. We describe two analytics-based solutions developed within IBM to address these related issues. The Web-based tool OnTARGET provides a set of analytical models to identify new sales opportunities at existing client accounts and noncustomer companies. The models estimate the probability of purchase at the product-brand level. They use training examples drawn from historical transactions and extract explanatory features from transactional data joined with company firmographic data (e.g., revenue and number of employees). The second initiative, the Market Alignment Program, supports sales-force allocation based on field-validated analytical estimates of future revenue opportunity in each operational market segment. Revenue opportunity estimates are generated by defining the opportunity as a high percentile of a conditional distribution of the customer's spending, that is, what we could realistically hope to sell to this customer. We describe the development of both sets of analytical models, the underlying data models, and the Web sites used to deliver the overall solution. We conclude with a discussion of the business impact of both initiatives.

Customer targeting models using actively-selected web content

“…Cross-validation showed that the OnTarget models out-performed the baseline consistently. We also compared the models in a more realistic setting, namely their success in predicting actual sales based on model scores computed in a previous quarter [9]. In this case, we also found that the OnTarget model dominantly out-performed the baseline, suggesting that the performance advantage, seen in statistical cross-validation, carried over to the actual deployment of the models.…”

“…The ROC curves in Figure 2 and 3 show the relative impact of building these composite model over using only firmographics or web content. In [9], we compared previous firmographic-based OnTarget models with a baseline model that simply ranks prospects by a measure of company size. Cross-validation showed that the OnTarget models out-performed the baseline consistently.…”

“…These estimates are the results of predictive modeling efforts on the combined information from IBM-internal databases (containing mainly sales history) and firmographics, that is, information on the companies which are potential IBM customers, which is purchased from data collection agencies such as Dun & Bradstreet (http:www.dnb.com) and Standard and Poor (http:www.standardandpoor.com). Several aspects of the methodology and results of OnTarget are discussed in our previous publications [15,9].…”

Medical data mining: insights from winning two competitions

“…A business intelligence example Modeling propensity to purchase IBM products by companies (Lawrence et al 2007), we defined x as the historical relationship a company has with IBM up to some fixed time t (say, end of year 2006), and its firmographics (i.e., characteristics of the company). The response y was the purchase of the product in some period t (say, 1 year) following t. However, in later work we sought to also utilize information from companies' websites to improve the model .…”

Prescriptive Analytics for Allocating Sales Teams to Opportunities

“…A piece of work that focuses more heavily on learning, looks at the relationship between product offerings and client characteristics, and at the estimation of revenue potential of clients rather than the relationship between the sales team composition and revenue as mediated by client characteristics [9]. The work of [10] considers a specialized form of a B2B sales response function in which there are only two options and in [11], although continuous sales response functions are learned, optimization is not considered.…”