Abstract

Lead generation is a very important aspect of business development and revenue generation for any company. For a higher number of deals to be closed, a lot of leads need to be generated. With a high volume of leads, it is impossible for a sales team to review each lead. Teams using a best-guess or first-come/first-served basis might not identify the best leads available. Similarly, using prior experience has the potential to cause important leads to be ignored. The number of features that can result in a favorable outcome for a given lead is large, complicated, and not deterministic, which, thus, introduces a problem that cannot be solved basic computational logic. Presented herein are techniques through which a number can be assigned to a lead using a machine learning (ML) algorithm that outputs a number that is directly proportional to probability of the lead being converted to a favorable outcome (e.g., sales, etc.). Such prioritization of leads can help a sales team converge on important leads first and not miss out on an opportunity to convert the leads. Further, by setting the ML algorithm in a continuous learning mode, the ML model will always be up-to date and can learn newer features. Feedback mechanisms can also be utilized (e.g., using a correlation of features with outputs) to further improve lead quality, thereby improving lead convergence.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS