Explainer: under the hood of deal likelihood scores

We measure our model precision for positive predictions by asking, “Out of all deals we gave a high likelihood score, how many predictions were correct?” (More info on how we measure the model is coming soon.)

The results show we have high precision, which indicates a low rate of false positives.

On average, Gong AI is 21% more precise than sales reps in predicting winning deals, as early as week 4 in the quarter. Our results are based on a test set of thousands of deals.

Naturally, no score is perfect. There may be activities on a deal that we don’t track or know about that affect the score positively or negatively.

Our base model is lab-trained on the complete life cycle and behavior of both won and lost deals, across a large number of customers. By studying billions of interactions, the model gets a deep understanding of the nuances of each signal, and how they contribute to whether or not the deal is won.

Next, the base model is customized for your business. By looking 2 years back at all the deals closed in your company specifically, we understand how variables that are unique to your business affect typical deal performance in your world.

In this step, we train the model on variable signals such as:

To ensure you get an accurate score every single day, the AI runs on both models every day. This ensures Gong AI is constantly up to date with the latest developments in each deal, and also, the AI is up to date with the past 2 years of information, including what happened yesterday.