DSN AI Bootcamp Qualification Hackathon by Data Science Nigeria
Predict customers who will default on a loan
888 data scientists enrolled, 521 on the leaderboard
Financial ServicesPredictionStructured
9 September—3 October
Ends in 8 days
How to improve score some suggestions plz
published 15 Sep 2020, 17:21

Actually i am a beginner and i am not familar with preprocessing,i fill missing values with mean and median then i apply PCA to the dataset and then i apply ML models like logistic regression and KNN but score not increases it is stops at 62 any suggestions to improve my model

Possible improvement

1.EDA improvement

2. fill in the missing value

3.handle outlier

4. features selection

Try using Gradient Boosting Algorithms like catboost, xgboost,lightgbm e.t.c

i tried using both catboost and xgboost but got a lower score. I also got a lower score when i used mean and median for filling the missing values.