Bryan Stevanus
Data Analyst & Scientist
New to Contra
Bryan is ready for their next project!
House Rent Prediction System with Machine Learning
Developed a house rent prediction system that estimates rental prices based on property characteristics such as location, size, number of rooms, furnishing status, and tenant preference. The project combines data analysis, visualization, and deep learning to uncover rental patterns and generate accurate predictions.
I conducted exploratory data analysis to compare rental prices across major cities and housing features, then built a neural network model using LSTM to learn complex relationships within the data. The final model allows users to input housing details and receive an estimated rent value.
https://github.com/bryan781/House-Rent-Prediction-using-LSTM-.git
1
2
58
YouTube Engagement & Performance Analysis | Python
Analyzed YouTube video performance data using Pandas and visualization libraries to uncover engagement trends, category performance, and audience behavior insights. Built structured exploratory data analysis workflows to support data-driven content strategies.
https://github.com/bryan781/Youtube-Data-Analysis-using-Pandas-and-Google-API-Data.git
1
2
60
Accelerometer Time-Series Analysis | Python
Processed and analyzed accelerometer sensor data using Pandas and NumPy to extract motion features and visualize multi-axis acceleration patterns. Demonstrated time-series preprocessing and signal interpretation techniques.
https://github.com/bryan781/Accelerometer-Data-Analysis.git
1
2
69
Electric Vehicle Adoption Analysis | Python & Pandas
Analyzed EV population data to identify growth trends and regional adoption patterns. Cleaned and processed transportation datasets using Pandas and created visual insights into sustainability transitions and electric mobility growth
https://github.com/bryan781/Electric-Vehicle-Population-Data-Analysis.git
1
2
74
Birth Rate Trend Analysis | Python & Pandas
Analyzed global birth rate data using Python (Pandas, NumPy, Matplotlib) to uncover long-term demographic trends and regional differences. Performed data cleaning, time-series analysis, and visualization to generate insights into population growth patterns and socio-economic implications. Delivered clear visual storytelling through structured exploratory data analysis.
https://github.com/bryan781/Birth-rate-analysis-using-IPYNB.git
1
2
59
Unsupervised Learning Techniques to Analyze Amazon Customer Behavioral Data
This project applies unsupervised learning techniques to analyze Amazon customer behavioral data with the goal of discovering meaningful customer segments that can support engagement, retention, and personalization strategies.
Unlike supervised models that predict predefined outcomes, this study focuses on clustering, allowing hidden behavioral patterns to emerge naturally from the data. The analysis was conducted entirely in R, following a structured data science workflow from problem formulation to business recommendations.
https://github.com/bryan781/Unsupervised-Learning-Techniques-to-Analyze-Amazon-Customer-Behavioral-Data
1
2
68
📚 ASEAN Research Trends & Citation Impact Analysis (Information Science)
This project analyzes research trends, citation impact, and collaboration patterns in ASEAN information science journals using quantitative data analysis and text mining techniques. The study leverages Web of Science bibliographic data to examine how ASEAN research output has evolved over time and how international collaboration influences academic impact.
The analysis combines descriptive statistics, TF-IDF topic modeling, and regression analysis to identify emerging research areas, influential ASEAN countries, and key drivers of citation performance.
Link: https://github.com/bryan781/ASEAN-Research-Trends-Citation-Impact-Analysis-Information-Science-
1
2
59
📊 Customer Satisfaction & Churn Prediction using Machine Learning
This project analyzes Amazon customer behavior to predict customer satisfaction and churn risk using machine learning techniques. The study applies Logistic Regression and XGBoost models to identify key behavioral factors influencing customer retention and recommendation effectiveness.
Using an Amazon customer behavior dataset from Kaggle (2023–2024), the project combines exploratory data analysis (EDA), correlation analysis, and predictive modeling to support data-driven decision-making for e-commerce platforms.
Link: https://github.com/bryan781/Predicting-Customer-Churn-and-Recommendation-Likelihood-in-Amazon-Using-Machine-Learning
1
46
📊 Customer Satisfaction & Churn Prediction using Machine Learning
This project analyzes Amazon customer behavior to predict customer satisfaction and churn risk using machine learning techniques. The study applies Logistic Regression and XGBoost models to identify key behavioral factors influencing customer retention and recommendation effectiveness.
Using an Amazon customer behavior dataset from Kaggle (2023–2024), the project combines exploratory data analysis (EDA), correlation analysis, and predictive modeling to support data-driven decision-making for e-commerce platforms.
Link: https://github.com/bryan781/Predicting-Customer-Churn-and-Recommendation-Likelihood-in-Amazon-Using-Machine-Learning
2
50