# 37th place approach in the G-Research Crypto Forecasting Competition.

Congrats to the winners, and to the host for a great and interesting competition!
With some luck I made it to the 37th place, below is a short summary 🙂
In the G-Research Crypto Forecasting Competition I have done more human learning than machine learning, 99% feature engineering and data creation. I can now more of translations between Pandas, Polars and Rapids and tons of technical analysis. It’s always a human learning in machine learning. 👍🙂
Common way in general trading is using different TA indicators and strategies, so my approach was to create and tune different TA indicators in a MTF(MultiTimeFrame) strategy. However, the 0.25s/14 assets with the hw in use and time limit for total 3-month re-run was the biggest challenge, as we all struggled with, I guess. My ideas were to make a more bullish model and one that handles both markets. I used maximum 1440 minute period TF to minimize timeout.
TA indicators and feature engineering
Short summary as it was the biggest part:
I created and tuned TA indicators and features for every one of the 14 assets, this because maybe different TA techniques work better in one and worse in another and to have a more differed total portfolio in terms of input for the forecasts. Some feature creations also are more time expensive than other so choosing bigger and smaller feature engineering cross the test time managed the time out. Have also heard somewhere that it’s easy to overfit with too many indicators so I also had that in mind.
In crypto assets Litecoin and IOTA not much worked of the classic ones so here I use as much of TA the one can fill to get at least a score on the right side, used many of the original ones from baseline to get a balanced total approach to not get stuck in one idea.
To handle the outliers and extreme values I used calculated quantile cutoff for every asset. Maybe not the best and maybe can worsen the best scores but I hoped to balance and smoothing it more.
Models
Here I didn’t used much effort this time, afraid of overfit even more, so here I used an ensemble of one light tuned Xgb and one untuned Xgb but with different seeds. Also added two lgbm with different seed and minor differences. In total 4 models ensemble to the prediction.
Training
As many of us we had many solutions and ideas, but many went to trashcan as they didn’t meet the time limit, so I used the same solution for both submissions but trained with different datasets.
First submission trained only with the public period dataset and tuned for a more bullish market with a believe that TA works better in that market and second solution trained with the complete dataset with no overlap until evaluation period.
As validation during training, I manually picked different market condition to validate on, bullish, bearish and between.
Handling test time limit
I tried Pandas, Rapids and Polars and ended up with Polars that also have support for the Talib library used for many of indicators.
That’s it!
😊
Disclaimer
Disclaimers are always in place dealing with the subject if someone take it out of context, this approach is only for this competition and shouldn’t be taken for a real working end-to-end solution. So remember that all ideas and information presented are not recommendations or financial advice. Use at your own risk.