WIP. Here's what I'm working on. My original idea was to simulate 3-5 different car HMIs that each represented a diferent era. While gathering references I decided to focus on how speed was represented, what made you feel it. Because I wanted to create a driving simulator webapp where the user could really feel the adrnaline of going fast. With a better idea about the history of HMIs and representation of speed, I wanted to challenge myself a bit more by creating a scenario for a future where only EVs are allowed (so bye-bye cool tachometers!) and where autonomous agentic driving is the new norm. I put myself in the shoes of someone that has nostalgia about the past, the thrill of driving a car yourself and the adrenaline of going fast. Agentic driving (when you choose to take over the autonomous mode) would allow all drivers the ability to go ultra fast, safely, so you can arrive earlier to your target. So I focused on this journey: how to go from autonomous driving mode to manual mode and add a bit of gamification to the driving manually experience. The idea was to design 3 different manual driving modes: Analog Soul (essence of sports 70s and 80s cars), Digital Craze (the frenzy of flashy digital 80s and 90s car clusters) and Smart Drive ( 2030s. How does it look like to drive alongside an AI assistant?). For now, I have the autonomous driving state and the Analog Soul. I'm working on the transition between them. I don't think I'll be able to have the 4 different screens for the end of the challenge, but let's see. I wasted way too much time on the design phase... 🥲 I'll be posting the webapp at the last minute... I'm learning along the way. First time using Rive and, so far, I'm loving it! I don't find it very complicated, the tutorials from their site are great.

End-to-End Machine Learning Pipeline for Telecom Customer Churn

1. The Business Problem

Customer churn is a major challenge for telecommunications companies, driven by competition, service issues, and changing consumer preferences. This project was designed to transition the company from reactive support to proactive retention using data-driven strategies such as customer segmentation, personalized offers, and loyalty programs,.

2. Data Exploration & Insights (EDA)

I performed a comprehensive descriptive analysis on a database of 7,043 customers with 21 distinct variables,. Key findings included:

Contractual Risk: Customers on month-to-month contracts showed significantly higher churn compared to those on one- or two-year commitments,.

Service Preference: While Fiber Optic plans were the most popular, they also represented a critical segment for monitoring due to their higher price points,.

Financial Indicators: Churned customers had a higher average monthly charge of $74.44, compared to $61.27 for retained customers.

Payment Behavior: The "Electronic Check" payment method was most strongly associated with service cancellation,.

3. Engineering & Preprocessing Pipeline

To prepare the data for high-performance modeling, I implemented a rigorous preprocessing workflow:

Data Cleaning: Removed irrelevant identifiers like customerID and addressed potential data quality issues. The dataset was verified to have zero missing or NaN values,.

Feature Engineering: Applied Label Encoding to transform categorical text variables into a numerical format suitable for machine learning algorithms,.

Data Splitting: Adopted a standard 80/20 train-test split to ensure the model could generalize effectively to unseen data,.

4. Model Development & Benchmarking

I developed and benchmarked eight distinct machine learning algorithms to identify the most effective solution for this specific application:

Linear & Probabilistic: Logistic Regression, Naive Bayes.

Tree-Based: Decision Tree, Random Forest.

Boosting Frameworks: AdaBoost, Gradient Boosting, XGBoost, and LightGBM,.

5. Performance Evaluation & Results

Models were evaluated using ROC curves, confusion matrices, and detailed classification reports,.

Winner: Logistic Regression achieved the highest accuracy at 81.83%,.

Secondary Performers: Gradient Boosting (81.05%) and AdaBoost (80.98%) also showed strong predictive power.

6. Technical Conclusion

This data-driven approach proves that proactive churn prediction is essential for business sustainability. By identifying that customers prioritize high-speed fiber optic services but are sensitive to pricing and contract terms, the company can now optimize its pricing and retention strategies to maximize user satisfaction and revenue.