Slava Kurilyak

> Write some extra utils results (confussion matrix). I think creating an extra utility to understand the confusion matrix is a great idea to better understand performance of a classification...

@bukosabino Thanks for pointing this out! @treethought Is our infrastructure on Google Cloud Platform (GCP) scalable enough to handle minute trading?

Good point. We can also perform trades every 1-min, 2-min, 5-min, 10-min, 30-min, 1-hour, 2-hour, 6-hour, and 12-hour, 24-hour, or as often as we need to. I'm assuming that more...

@bukosabino We can use other libraries to perform automated machine learning (#25). These include, but are not limited to: [auto-sklearn](https://github.com/automl/auto-sklearn/), [scikit-optimize](https://github.com/scikit-optimize/scikit-optimize) and/or [osprey](https://github.com/msmbuilder/osprey).

Let's use **Total performance (%)** or **Total performance (net) (%)** to evaluate portfolio based on a time (last X minutes/days/weeks/months) (Inspiration: [Signals Network](https://signals.network/))

According to Marcos Lopez de Prado ([Advances in Financial Machine Learning, 2018](https://drive.google.com/open?id=1crbgAqZAbm8BVMNyOfEIL3j2uRgxxmeQ)), strategy performance is best calculated as: 1. **Time-Weighted Rate of Return (TWRR)**: Total return is the rate of...

@bukosabino For additional inspiration, check out the following three Github topics: [automated-machine-learning](https://github.com/topics/automated-machine-learning), [auto-ml](https://github.com/topics/auto-ml), [automl](https://github.com/topics/automl)

Consider using jhfjhfj1's [autokeras](https://github.com/jhfjhfj1/autokeras) or automl's [SMAC3](https://github.com/automl/SMAC3) libraries as well

Google releases [AdaNet](https://ai.googleblog.com/2018/10/introducing-adanet-fast-and-flexible.html), which incorporates AutoML with Tensorflow

Microsoft releases [nni](https://github.com/Microsoft/nni), an open source AutoML toolkit for neural architecture search and hyper-parameter tuning, with support for [Keras](https://github.com/Microsoft/nni/search?q=keras&unscoped_q=keras&type=Code), [Tensorflow](https://github.com/Microsoft/nni/search?q=tensorflow&unscoped_q=tensorflow&type=Code), [Pytorch](https://github.com/Microsoft/nni/search?q=pytorch&unscoped_q=pytorch&type=Code).