PROJECTS

Global Supply Chain Prediction for Healthcare Industry 
Client: Imperial Logistics, South Africa | January 2021– April 2022
    Applying the statistical analysis, pattern recognition, and machine learning along with domain knowledge and subject-specific models to solve the problems.
∑    Contributing to stages of data modelling and analytics projects, including problem formulation, solution development, and product deployment.
∑    Performing exploratory data analysis for improved understanding.
∑    Building, analysing, and comparing various machine learning models.
∑    Contextualizing the results and synthesizing them with existing
∑    knowledge or domain-specific models.
∑    Helping in deployment of model to end-users and submitting document data-analytic results in technical reports. 
ML Algorithms and tools used: NumPy, Pandas, Matplotlib, pyplot Scikit-learn, Seaborn, SVM, KNN, Linear and Logistic Regression, Random Forest, Extratrees Algorithm, XG Boost. 

Purchase Behaviour Segmentation and Churn Analysis  
Client: Wellbee’s Supermarket, Malta | March 2020– December 2020
∑    Reading and researching about the domain knowledge regarding
∑    the problem from domain expert and Research Papers. 
∑    Pre-processing and cleaning the data received from Data Engineer.
∑    Performing initial data investigation and exploratory data analysis.
∑    Choosing and performing various clustering techniques for segmentations and classification algorithms for churn prediction.
∑    Comparing the results and communicate the findings.
∑    Helping in deployment of model to end-users and submitting document data-analytic results in technical reports. 
ML Algorithms and tools used: NumPy, Pandas, Matplotlib.pyplot Scikitlearn, Seaborn, K-Means Clustering, Logistic Regression, Random Forest, XGB Classifier.

Predictive Modelling for Credit Risk Analysis  
Client: Taichung Bank, Taiwan | July 2019– February 2020 
∑    Gaining the domain knowledge regarding the financial sector and risk analysis from domain expert and Research Papers. 
∑    Performing statistical data analysis, data pre-processing and feature engineering. 
∑    Contributing to stages of data modelling and analytics projects, including problem formulation, solution development, and product deployment 
∑    Performing feature selection and applying various classification models on data for improved accuracy. 
∑    Comparing the results and communicate the findings to the team and present it to client. 
∑    Helping in deployment of model to end-users and submitting document data-analytic results in technical reports. 
ML Algorithms and tools used: NumPy, Pandas, Matplotlib.pyplot, Scikit-learn, Seaborn, Logistic Regression, Random Forest, Extra Trees, AdaBoost Classifier, XGB Classifier.