DataDrive2030-Early-Learning-Predictors-Challenge

The solution is very simple

• Reading files

• Explore data analysis

• Some feature engineering techincques

• Evaluating model

• Model prevew and prepare it for submission

• This solution will get me first place

This comptetion

About data from multiple programmes and projects who used the ELOM tools were collated, spanning from 2019-2022. You can view the different data sources and collection methods in a PDF in the download section.

There are 8 665 children in the train and 3 600 in test.

In this competition, we aim to use machine learning techniques to identify factors of early learning programmes that contribute to better learning outcomes in children. While predicting the child’s ELOM score and the top 15 predictors for each child.

The final merged dataset consisted of 12 265 children across 2 217 facilities. Table X below provides a summary of the data included in the meta-dataset. The first column indicates the data source, and the remainder of the columns show the different types of tools or data collected and the number of children we have data for across these sets of variables. An “X” indicates that the data was not collected at all.

comptetion link https://zindi.africa/competitions/datadrive2030-early-learning-predictors-challenge/data