Skip to content

airaghidavide/financial-inclusion-app

Repository files navigation

Financial Inclusion classifier - App

🏆 Mentioned in streamlit weekly roundup: https://discuss.streamlit.io/t/weekly-roundup-memory-usage-improvements-molecule-stl-files-plotting-apps-and-more/18624

Open in Streamlit Open In Colab Made withJupyter

Context

Financial inclusion remains one of the main obstacles to economic and human development in Africa. For example, across Kenya, Rwanda, Tanzania, and Uganda only 9.1 million adults (or 14% of adults) have access to or use a commercial bank account.

Traditionally, access to bank accounts has been regarded as an indicator of financial inclusion. Despite the proliferation of mobile money in Africa, and the growth of innovative fintech solutions, banks still play a pivotal role in facilitating access to financial services. Access to bank accounts enable households to save and make payments while also helping businesses build up their credit-worthiness and improve their access to loans, insurance, and related services. Therefore, access to bank accounts is an essential contributor to long-term economic growth.

Objective

The objective is to create a machine learning model to predict which individuals are most likely to have or use a bank account. The models and solutions developed can provide an indication of the state of financial inclusion in Kenya, Rwanda, Tanzania and Uganda, while providing insights into some of the key factors driving individuals’ financial inclusion.

Description

The machine learning model experiment is developed on a dataset provided from https://zindi.africa/ and the data was extracted from various Finscope surveys ranging from 2016 to 2018. Once the best model has been validated, it has been saved and used by the web app developed using the framework Streamlit in order to perform on-line single prediction allowing the user to change the features and get the result.

Methods Used

  • Exploratory data analysis
  • Machine Learning
  • Predictive Modeling
  • Model deploying

Technologies

  • Python
  • Jupyter Notebook
  • Streamlit
  • CI/CD

Useful Projects

Name Link
pandas profiling https://github.com/pandas-profiling/pandas-profiling
pdpipe https://pdpipe.github.io/pdpipe/
catboost https://catboost.ai/
streamlit https://streamlit.io/

App

Alt Text