Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

AbdullahMahar2004/Financial-Inclusion-in-Africa-Zindi-solution

Domain:

socioeconomic

Record type:

project
Creator:
Abd
Host:
# Financial Inclusion in Africa - Zindi Competition This repository contains my solution for the Financial Inclusion in Africa machine learning competition hosted on Zindi. The goal of the competition was to predict which individuals are most likely to have or use a bank account, based on demographic and socio-economic data from several African countries. ## Competition Overview - **Objective:** Predict bank account ownership for individuals in Kenya, Rwanda, Tanzania, and Uganda. - **Data:** Includes demographic, socio-economic, and household information. - **Evaluation Metric:** Binary classification accuracy (and log loss). - **My Result:** 🏅 **12th place** on the final leaderboard. ## Repository Structure - `Train.csv`: Training data with features and target variable (`bank_account`). - `Test.csv`: Test data for final predictions. - `VariableDefinitions.csv`: Detailed description of each variable. - `SampleSubmission.csv`: Example of the required submission format. - `submission_enhanced.csv`: My final enhanced submission. - `AfricaClassifier.ipynb`: Main notebook containing data exploration, preprocessing, modeling, and submission generation. - `README.md`: This file. ## Approach 1. **Exploratory Data Analysis (EDA):** - Analyzed distributions, missing values, and relationships between features and the target. - Visualized categorical and numerical variables. 2. **Feature Engineering:** - Label encoding and one-hot encoding for categorical variables. - Standardization of numerical features. - Handling of missing values and rare categories. 3. **Modeling:** - Used LightGBM for binary classification. - Hyperparameter tuning and cross-validation. - Special handling for "uncertain" prediction cases using conservative and aggressive models for borderline probabilities. 4. **Submission:** - Generated predictions in the required format. - Analyzed and compared the impact of enhanced uncertainty handling. ## Results - Achieved **12th place** on the Zindi le …

Visit

github.com

Tasks

text classification

Similar

ShowBaba/Zindi-Financial-Inclusion-in-AfricaSirDamis/Financial-Inclusion-in-Africa-ZindiBonifacethuo/Financial-Inclusion-in-Africa-ZindiLemukong/Zindi-Financial-Inclusion-in-AfricaPayalSorathiya/Zindi-Financial-Inclusion-in-AfricaByabato/financial-inclusion-africa-ml-zindi

ShowBaba/Zindi-Financial-Inclusion-in-Africa

My solution to the Financial Inclusion in Africa Zindi challenge # Zindi-Financial-Inclusion-in-Afr

SirDamis/Financial-Inclusion-in-Africa-Zindi

# Financial-Inclusion-in-Africa-Zindi Financial Inclusion remains one of the main obstacles to econo

Bonifacethuo/Financial-Inclusion-in-Africa-Zindi

# Financial-Inclusion-in-Africa-Zindi In this project, the objective was to develop a machine lear

Lemukong/Zindi-Financial-Inclusion-in-Africa

Competition to create a machine learning model to predict which individuals are most likely to have

PayalSorathiya/Zindi-Financial-Inclusion-in-Africa

# Zindi Financial Inclusion in Africa A machine learning project to predict which individuals are m

Byabato/financial-inclusion-africa-ml-zindi

End-to-End ML Pipeline & Policy Intervention Simulator for Financial Inclusion in East Africa. Featu