Here is a short intro on the theory of Gradient Boosted Decision Trees: https://developers.google.com/machine-learning/decision-fore...

And here is a practical intro to it, you can run it right in your browser if you open it in Colab: https://www.tensorflow.org/decision_forests/tutorials/beginn...

Kaggle.com. Sign up to a competition or download a dataset.

Install python 3.11, and the libraries sklearn, lightgbm, pandas, matplotlib and numpy

Ask a LLM to write a python script that loads the data and fits a model to the data and summarizes/plots some results.

Jupyter Lab with autoreload, and using a python virtual environment are recommended.

(temporian developer here)

Here's a simplified version of the approach (i.e. performing strong feature engineering, then converting the multivariate time series data to a panel/tabular dataset and training a boosting trees model on it), using temporian (a much improved alternative to pandas for working with temporal data) and xgboost: https://temporian.readthedocs.io/en/stable/tutorials/m5_comp...

If you're talking about Gradient Boosting, I've a somewhat popular answer on Quora from ages ago [1].

[1] https://qr.ae/pKJPbm

Maybe check out this recap on the M5 competition? It has links to notebooks and some of the top solutions.

https://www.kaggle.com/competitions/m5-forecasting-accuracy/...

i'm using this tutorial to get started: https://www.youtube.com/watch?v=Wqmtf9SA_kk

I used to be an xgboost bro but these days I'm schilling for catboost. Anyways both have lots of examples online. The truth is without a problem interesting to you there's not much reason to learn about them unless you simply find gradient boosting algorithm elegant. Otherwise I would take some intro to machine learning course.

> used to be an xgboost bro

You sound like a moron.

Thanks internet stranger.