Mohamad Rizal Syafi'i
Machine Learning
Churn Mitigation
This project uses machine learning models to predict customer churn by analyzing behavioural and demographic data, such as Feature Engineering, Exploratory Data Analysis, Machine Learning Model, and Model Evaluation. This predictive analytics approach helps businesses identify customers who are likely to churn and develop targeted retention strategies.
Water Quality
This project leverages machine learning to classify drinking water quality based on various physicochemical properties, such as Feature Engineering, Exploratory Data Analysis (EDA), Machine Learning, and Model Deployment. This predictive model helps in determining whether water is safe for consumption or not based on specific chemical compositions.
Heart Disease
This project leverages Decision Tree and Support Vector Machine (SVM) models to analyze key cardiovascular risk factors and provide interpretable insights for heart disease prediction. The goal is to create an explainable and effective predictive model that helps in identifying individuals at risk of heart disease, contributing to proactive healthcare strategies.
Three Datasets
This project demonstrates Naive Bayes, Decision Trees, and Regression models using well-known datasets from Scikit-Learn, such as Naive Bayes on the Iris Dataset, Decision Tree on the Breast Cancer Dataset, and Regression Analysis on the Diabetes Dataset. This project is valuable for machine learning students to understand different ML models.
Harvesting Price
This project leverages machine learning techniques to predict rice prices based on historical data from Badan Pusat Statistik Indonesia, such as Rice Price Forecasting and Data Analysis. This project is valuable for farmers, traders, policymakers, and businesses to make informed decisions based on price trends.
Mapping Customer
This project leverages PySpark's scalable computing power to perform customer segmentation using the K-Means clustering algorithm, such as Customer Segmentation and Distributed Computation. This project is valuable for business analysts, marketers, and data scientists to understand customer behaviour better and improve targeted marketing strategies.
