Without the right data, every sales force will struggle to achieve their maximum potential. Lacking the best data and tools, they will instead fall back on sales methods based on experiential judgment or on the static rules of heuristics.
Predictive modeling was employed to help one company achieve breakthroughs in predictive selling via two models:
- A persuasion model that identifies willingness to purchase through CHAID decision trees
- A credit model that identifies ability to purchase through logistic regression
These models were derived using a nationally-representative survey sample of ~6,500 individuals from which 115M+ households were scored. Custom heat maps (using R) were then built to fuel better decision making.
- How to incorporate secondary household data with your primary research to make it more actionable.
- Applying advanced analytics to your primary research data.
- Leveraging data visualization in R.