Applied Data Science Lab: Predicting Spotify Likes

Session 3: Machine Learning Model Development and Evaluation
Join us for the third session of our hands-on lab, where we’ll take the next big step—developing and evaluating a machine learning model. In this session, using the feature selection and feature engineering we performed previously, we’ll build predictive models, fine-tune their performance, and assess their effectiveness using key evaluation metrics. These insights will prepare us for the final phase—deploying the model in Session 4.
Continuing with Spotify’s song data, we’ll train models to predict whether a song will be “liked” based on its audio features, refining our approach to achieve the best results.

We’ll use Python, Pandas, Matplotlib, and Scikit-learn to build our model.

Who Should Join?
These labs are designed for data enthusiasts and aspiring data scientists looking to gain hands-on experience with real-world projects. These labs are typically held over four sessions.
Prerequisites: A basic understanding of Python and Pandas will help you get the most out of the labs.
Install: Anaconda

Format:
🔹 Session 1: Project Overview and Dataset Introduction
🔹 Session 2: Exploratory Data Analysis (EDA) and Feature Engineering
🔹 Session 3: Machine Learning: Model Development and Evaluation
🔹 Session 4: Model Deployment and Final Insights

Goal of the Applied Data Science Labs
The goal of these labs is to provide a supportive, hands-on environment where learners can practice, experiment, and apply their data science knowledge with guidance from mentors and peers. Whether you're new to the field or looking to strengthen your skills, these labs offer the opportunity to work with real-world datasets and explore key areas like data wrangling, statistical analysis, data visualization, and machine learning. Through guided projects and collaborative exercises, participants can develop a portfolio that showcases their growing proficiency while building confidence in using popular data science tools.

We hope you join us!

AGENDA

• 6:00 p.m. – Welcome
• 6:05 p.m. – Review Session 2
• 6:20 p.m. – Machine Learning and Algorithms Overview
• 6:40 p.m. – Model Training & Evaluation
• 6:50 p.m. – Identifying the Most Important Features
• 7:00 p.m. – Model Tuning
• 7:10 p.m. – Preview of the final session
• 7:20 p.m. – Questions/Discussion
• 7:30 p.m. – End