Evaluation

The objective of the competition

The goal of the participant is to perform binary classification [0, 1] on a universe of startups.

This requires submitting the exact value of 0 or 1 for each investment opportunity (row of the dataset). Startups labeled as 1 are expected to achieve higher valuations, while those labeled as 0 are not anticipated to experience significant valuation growth.

The ensembling of all the submissions will allow identifying which investments are likely to perform better than others by ranking them according to the overall community consensus on each opportunity.

The scoring metric

This competition is evaluated on the F1 score.

$$F1 = \frac{2*Precision*Recall}{Precision+Recall}$$

Where:

$Precision = \frac{TP}{TP+FP}$

$Recall = \frac{TP}{TP+FN}$