Data Science Enthusiast & Computer Engineering Professor | Python, ML

projects

github

Backend Engineer & Computer Engineering Professor | Presently shifting to MLE career | CLSSGB

Francis Ignacio • Peerlist Profile

Customer churn, the phenomenon where customers stop doing business with a company, is a critical issue for many businesses. Predicting which customers are likely to churn can help companies take proactive measures to retain them, thereby improving customer satisfaction and business profitability. In this notebook, we will build a Customer Churn Prediction model using an Artificial Neural Network (ANN).We will use a dataset containing various features about customers, such as their credit score, geography, gender, age, tenure, balance, number of products, whether they have a credit card, whether they are active members, and their estimated salary. The target variable is whether the customer has exited (churned) or not.The steps involved in this notebook include:1. Importing necessary libraries and setting up the environment.2. Loading and exploring the dataset.3. Preprocessing the data to make it suitable for training the ANN.4. Building and training the ANN model.5. Evaluating the model's performance.6. Making predictions on new data.By the end of this notebook, you will have a robust model that can predict customer churn with a high degree of accuracy.

Customer Churn Prediction using ANN

Explore into the exploration and preparation of a dataset focused on gastric cancer prediction. By importing essential libraries and analyzing the dataset, we begin by performing an in-depth exploratory data analysis (EDA) to understand the structure and characteristics of the data. The dataset comprises various microRNA-target interaction predictions, which are crucial for understanding gene regulation mechanisms related to gastric cancer.

Gastric Cancer Prediction

This report provides a comprehensive analysis of factors influencing high school students' academic performance using a dataset containing various demographic and behavioral attributes. The workflow includes importing necessary libraries, loading and exploring the dataset, visualizing data distributions, performing correlation analysis, and conducting detailed data preprocessing. Key predictive modeling techniques are employed to understand and predict GPA based on multiple variables.

Factors Influencing High School Students' Academic Performan

Analyze the cost of living indices across countries and predict cost of living categories&nbsp;(Low,&nbsp;Medium,&nbsp;High)&nbsp;using a Random Forest classification model and other models as comparison.&nbsp;Address class imbalance using SMOTE and optimize model performance through hyperparameter tuning.

Cost of Living Index Analysis

In this analysis, I explored a dataset on community crime statistics in Calgary with the goal of forecasting future monthly crime counts. The dataset contains records of crime occurrences across different communities, categorized by type, year, and month. The task required cleaning and analyzing this data and then building a predictive model to forecast future crime counts.