Wanna learn how to apply these 4 tips to a real-world dataset? In The Real-World ML Tutorial, you will do exactly that. Use the discount code IWANNAIT and get a 20% discount at checkout ↓ https://t.co/mU2zUkc055

Tip #2. Add more features to the dataset. The more features you add, the higher the chances your representation of the problem/phenomena is complete enough, so your algorithm will work. You can add features by → pulling in external data, or → with feature engineering. https://t.co/DcVlD1RKmb

Wanna get more real-world ML content? Follow me @paulabartabajo_ so you do not miss what's coming next. Wanna help? Like/Retweet the first tweet below to spread the wisdom ↓↓↓ https://t.co/nS2IKGad2G

Tip #4. Find the best hyper-parameters for your algorithm and dataset. Every ML algorithm has a set of parameters that you need to set BEFORE you train the model. You can find the optimal hyper-parameters using a library like Optuna. https://t.co/AwfSD29qOs

Tip #1. Add more samples to the dataset The more samples you feed to your algorithm, the higher the chances the algorithm picks up the patterns in the data. If you work with a tabular dataset, this means you wanna have more rows in your data. https://t.co/oOKd60JWus

Tip #3. Try another algorithm There are lots of algorithms you can try. However, for most tabular datasets, boosting tree algorithms (e.g. XGBoost) are usually the best. If a boosting algorithm does not work with your dataset, focus on improving the data, not the model. https://t.co/AfZHU7elCx

4 tips to improve your Machine Learning model 🧵 ↓↓↓

Your model performance is the end result of combining 2 basic ingredients: → a dataset, and → an algorithm If you wanna improve your model results, you need to improve either one of these 2 things. And here are 4 tips to do so ↓ https://t.co/tNYJ1ZQVdG