FIA is the Machine Learning powered wep App developed using streamlit framework.
Deployment Demonstration and building Machine learning using python , this repository demonstrates a use case for data scientist tasks of building model and deploy on cloud services to be accessed from different location on real time.
Financial Iclusion in Africa was the competition organised by zindi Africa which the main objective was required to build Machine Learning Model to predict the llikehood of an Individial to posses an bank Account or to use a bank account. The models and solutions developed can provide an indication of the state of fincial inclusion in kenya , Rwanda ,Tanzania and Uganda, while providing insights into the key factors driving individuals fincial security.
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.
Dataset from zindi Africa competion - Financial Inclusion in Africa.
- You can access the complete App here
- It has two options online and Batch predictions
- Online prediction can be done by filling individual details then perform prediction but this can not be effective to the one having records on spreadsheets.
- Batch prediction - here you can upload your spreadsheet with multiple individual detail and prediction can be done onces for all.
- After filling all fields you can preview details, then hit predict button.
On modelling part i have used RandomForestClassifieralgorithm since it was classification task , before selecting RandomForestClassifier i tried other algorithms such as Decisin Tree,Adaboost,Logistic Regression,SVM but RandomForestClassifier proved to be better compared to other algorithms using Accuracy as Evaluation Metric.
You can test the Web App here
