There was a time when I worked in data for a seed venture capital firm. Part of my job in the VC fund was to discuss with entrepreneurs the indicators of Product-Market Fit in their business. I used to apply the Quantitative Approach to Product Market Fit by Andrew Chen. We first discussed the indicators of product market fit with the entrepreneurs and then asked them for raw data of their users. I then played with the data to find the evolution of different users and their behavior in time.
There are mainly two types of representation in that quantitative approach: Accounting for Growth and Cohorts Analysis. In a startup, raw data is usually messy so I needed to code everything again and again to be able to fit the data. However, some weeks ago I dusted off my old notebook. With time and perspective, I decided to generalize the framework and create Python objects that are easier to use. In that way, you will only need to clean and prepare the datasets. The visualizations are done!
I coded two objects: one for Accounting for Growth and the other for Cohorts. They are built in a machine learning style, so you can set the parameters, fit the object with your data, and then ask for results and visualizations. Distribution of…