- A B2B software company wanted to leverage their sales pipeline data to see how certain factors affected the outcome of an opportunity and to use machine learning to predict sales opportunities with the best chance of closing.
- Aptitive leveraged a machine learning framework to implement a solution that would analyze the data and predict if an opportunity would be won or lost. We also implemented a Power BI dashboard that was used to prioritize pursuits and gain an enhanced understanding of behaviors that created wins.
- Our solution generated a numerical score from our client’s pipeline data to predict the outcome of an opportunity with 90% accuracy. The ease of use allowed the in-house analysts to run their own predictions and discover patterns to inform their decisions on a daily basis.
Just the Headlines
Short on time? Here are the key facts.
Microsoft SQL Server
A B2B software company wanted to leverage the data they had collected from their sales pipeline to better manage and prioritize open opportunities.
Although the company had a wealth of data on their sales opportunities, the large number of opportunities, high variability, and number of possible combinations made it nearly impossible for the sales team to see how these factors affected the outcomes of opportunities. The company knew they could improve their sales process and success rate if their sales team could easily analyze and leverage this data.
Aptitive’s machine learning framework was used to implement a solution to analyze the data and predict if an opportunity would be won or lost. The framework leverages SQL Server’s built-in machine learning services, which allows us to leverage open source machine learning algorithms implemented in R by Microsoft to build predictive models.
Examples of Data Collected
|Static Data||Dynamic Data|
|Company size||Contact with sales|
|Industry||Engagement with emails|
|Customer type||Length of time between stages|
We used machine learning to predict sales opportunities, employing our client’s historical opportunity data to generate a numerical score that was capable of determining the outcome of an opportunity with 90% accuracy. This score was augmented with data from the data warehouse and implemented in a Power BI dashboard that was used by the sales organization to prioritize pursuits and gain enhanced understanding of behaviors that lead to wins.
The ease of use allowed in-house analysts to run their own predictions and conduct additional analysis to discover patterns and causal effects. The machine learning generated score and related insights were integrated in the dashboards used by the sales team and inform their decisions on a daily basis.