Lead scoring
Many organizations score leads based on their activities (such as the pages they look at, if they download whitepapers or if they click on a link in an email). This helps prioritize those leads that are most likely to purchase. However, these scores are purely based on past actions. The real goal is to prioritize those prospects most likely to close in the near term. AI can use the same data to produce more accurate scores.
Overview
Predict the likelihood of a prospect closing or the expected value of a prospect to prioritize leads.
TARGET
Does a lead close or what is the deal size for the prospect
Challenge
Many companies start lead scoring with the data contained in the CRM. This data needs to be merged with the marketing data (which itself needs to be aggregated) to add the effect of outbound message on the leads. Next, web analytics data (again aggregated) should be joined as understanding the customers search for information on the website can provide key information about purchase intention. All this data needs to be cleaned, joined and transformed into valuable ML features before going into model training. This pre-modeling prep process can be frustrating and time consuming. We are here to help.
Modeling techniques and libraries
Machine learning analysis
Build machine learning models to predict the target as a function of the independent variables. Use model interpretability packages to evaluate the impact of the independent variables on the prediction.
Packages:
- Sklearn
- ELI5
- LIME
- SHAP
