video1.0<iframe src="https://www.loom.com/embed/7a476ed6dc1840b88066b8faf65ae313" frameborder="0" width="1282" height="961" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9611282Loomhttps://www.loom.com9611282https://cdn.loom.com/sessions/thumbnails/7a476ed6dc1840b88066b8faf65ae313-1713547897406.gif139.917In this video, I discuss an employee retention use case where a client wants to model the probability of staff retention or departure based on various factors. I explain how Active graph can be easily integrated into Python models to test edge cases and develop proof of concepts quickly. This use case allows clients to iterate and perform what-if analysis on predictive models, providing them with more value. I also share an actual model we ran to illustrate the effectiveness of this use case. Watch the video to learn more and try the use case yourself.