We incorporated three binary flags into our model to represent the presence of founders' social media links. For categorical variables, the most frequent value from the list was used, and the median for numerical variables.
Functions that generate features based on the founders' and investors' data incorporate a date parameter as input to prevent the model from using future information.
It is crucial to emphasize that all features related to a company's investment rounds should be captured in the dataset to enhance the prediction model.
The article highlights the importance of feature aggregation and careful selection to avoid information leakage and improve the accuracy of the prediction model.
[
Collection
]
[
|
...
]