Say Goodbye to Collapsed Metrics: Track Your Time-Series Predictions over Time (appliedexploration.com) 9 points by szemy2 3y ago ↗ HN
[–] szemy2 3y ago ↗ Hi HN,We realised that tracking the performance of our predictions over time was crucial to choose, debug and fine-tune our forecasting model.So we built Krisi (https://github.com/dream-faster/krisi) to help you with tracking metrics over time and generate informative reports.We'll be here answering questions - would love to hear your feedback! [–] szemy2 3y ago ↗ We also used krisi to run this Energy Forecasting walkthrough: https://colab.research.google.com/drive/1CVhxOmbHO9PvsdHfGvR... [–] szemy2 3y ago ↗ Krisi is also licenced under MIT with Commons Clause.
[–] szemy2 3y ago ↗ We also used krisi to run this Energy Forecasting walkthrough: https://colab.research.google.com/drive/1CVhxOmbHO9PvsdHfGvR...
[–] legothief 3y ago ↗ Hi! I'm also here (other co-founder of the company/project), we'd love to understand if this is a problem only we encountered - or others also need to keep track of their simulated model performance over time!
4 comments
[ 4.5 ms ] story [ 20.9 ms ] threadWe realised that tracking the performance of our predictions over time was crucial to choose, debug and fine-tune our forecasting model.
So we built Krisi (https://github.com/dream-faster/krisi) to help you with tracking metrics over time and generate informative reports.
We'll be here answering questions - would love to hear your feedback!