produvia / kryptos

Kryptos AI is a virtual investment assistant that manages your cryptocurrency portfolio
http://twitter.com/kryptos_ai
MIT License
48 stars 8 forks source link

Machine Learning Based Indicators Extraction #64

Open slavakurilyak opened 6 years ago

slavakurilyak commented 6 years ago

User Story

As a machine learning developer, I want to use technical indicators as features for machine learning algorithms.

As a machine learning developer, I want to select combination of indicators and then use machine learning algorithms to find the most profitable patterns of indicators. (Leung et al., 2000; Thawornwong et al., 2004)

As a machine learning developer, I want to use indicators as features and predict the target of pricing data in an attempt to extract the non-linear relationships between indicators. (Indera et al., 2017; Shynkevich et al., 2017)

As a machine learning developer, I want to deploy machine learning models to answer the following questions:

  1. Which combination of technical indicators to try (e.g. relative strength index and moving average)?
  2. What kind of parameters for the indicators will you use (e.g. size of time window)?
  3. What kind of machine learning algorithm to try (e.g. gradient boosting)?
  4. What kind of parameters for the algorithms to try (e.g. maximum depth)?
  5. Will you learn on the whole historical data, or just on past few months? Or will you always learn only on past few days and predict the next day?
  6. What will be your target? How will you define the buy/sell signal?

Inspiration

The user selects the indicator of their preference when determining a cryptocurrency trading strategy.