No amount of theory can replace hands-on practice. Textbooks and courses can give you the illusion of mastery because the material is right in front of you. But when you try to apply it, you might find it’s harder than it seems. "Projects" can help you rapidly improve your applied ML skills while giving you the opportunity to explore interesting topics. Additionally, you can add projects to your portfolio, making it easier to find a job, land cool career opportunities, and even negotiate a higher salary. In this article, we’ll introduce 8 interesting machine learning projects for beginners. You can complete any of them in a weekend or, if you really like them, expand them into longer projects.
- Machine Learning Gladiator
We affectionately call this "Machine Learning Gladiator," but it’s nothing new. It’s one of the quickest ways to build practical intuition around machine learning. The goal is to take out-of-the-box models and apply them to different datasets. This project is great for three main reasons: First, you’ll build an intuition for how models fit problems. Which models are robust to missing data? Which models handle categorical features well? Yes, you can flip through textbooks to find the answers, but you’ll learn better by doing. Second, this project will teach you the valuable skill of rapid prototyping. In the real world, it’s often hard to know which model performs best without simply trying them. Finally, this exercise can help you master the workflow of model building. For example, you’ll start practicing…
- Importing data
- Cleaning data
- Splitting it into train/test or cross-validation sets
- Preprocessing
- Transforming features
- Feature engineering
Because you’ll be using out-of-the-box models, you’ll have the opportunity to focus on honing these crucial steps. Check out the sklearn (Python) or caret (R) documentation pages for instructions. You should practice regression, classification, and clustering algorithms.
Tutorials
- Python: sklearn – Official tutorial for the sklearn package
- Predicting Wine Quality with Scikit-Learn – Step-by-step tutorial for training a machine learning model
- R: caret – Webinar provided by the author of the caret package
Data sources
- UCI Machine Learning Repository – Over 350 searchable datasets covering almost every topic. You’re sure to find a dataset that interests you.
- Kaggle Datasets – Over 100 datasets uploaded by the Kaggle community. There are some really interesting ones here, including PokemonGo spawn locations and San Diego’s tacos.
- data.gov – Open datasets released by the US government. If you’re interested in social sciences, check it out.
- Playing Moneyball
In the book "Moneyball," the Oakland A’s revolutionized baseball by analyzing player scouting. They built a competitive team while spending only 1/3 of the salary that large-market teams like the Yankees were paying. First, if you haven’t read this book, you should. It’s one of our favorites! Luckily, there’s a wealth of data available in the sports world. Data on teams, games, scores, and players can all be tracked online and accessed for free. For beginners, there are many interesting machine learning projects. For example, you could try…
- Sports betting… Predicting box scores based on available data before each new game.
- Talent scouting… Using college statistics to predict which players will have the best careers.
- General management… Creating clusters of players based on their strengths to build a well-rounded team.
Sports is also an excellent area to practice data visualization and exploratory analysis. You can use these skills to help you decide what types of data to include in your analysis.
Data sources
- Sports Statistics Database – Sports statistics and historical data covering many professional sports and some college sports. The clean interface makes web scraping easier.
- Sports Reference – Another sports statistics database. The interface is more cluttered, but individual tables can be exported as CSV files.
- cricsheet.org – Ball-by-ball data for international and IPL cricket matches. CSV files are available for IPL and T20 international matches.