firmai / financial-machine-learning Goto Github PK

per @firmai suggestion

It would be good if we could use github actions to pull in the most spoke about (using twitter etc) research papers on arxiv and ssrn, i.e. a subsection acting like an academic version of https://quantocracy.com/

Steps to accomplish this

• 1. leverage webservice api to query relevant topics and store results

  a. https://arxiv.org/help/api/basics#community
  b. SSRN doesn't seem to have api, so may need crawler

• 2. create github actions to pull in latest periodically

• 3. format as README or Wiki page and link from front page

• 4. Review the paper, list out main findings and approaches taken, maybe even assign relevance score on different sections, and tag labels (not sure how this is done yet)

This issue can be broken down to smaller issues if needed and If you would like to contribute to this task, please let @firmai or @bin-yang-algotune know

• change the font size to small
• automatically generate status (with 3 years = active)

Trading

• Deep Learning
• Reinforcement Learning
• Other Models
• Data Processing Techniques and Transformations

Portfolio Management

• Portfolio Selection and Optimisation
• Factor and Risk Analysis:

Techniques

• Unsupervised:
• Textual

Other Assets (consider renaming this to asset classes)

• Derivatives and Hedging:
• Fixed Income
• Alternative Finance

Others

• Extended Research:
• Courses
• Data
• Personal Papers
• Colleges, Centers and Departments
• Financial Engineering courses ranking etc. (new)
• Academic scans (new)

I watch a lot of repos like this for seeing what kind of projects have been added. But this one has a bot that generates a huge diff every day, making it pointless to watch for me. So the current repo is only useful for a one time browse, useless for watching for updates.

I saw that you liked my work, I like that you have looked at it https://github.com/Leci37/LecTrade/tree/develop

My name is Luis, I'm a big-data machine-learning developer, I'm a fan of your work, and I usually check your updates.

I was afraid that my savings would be eaten by inflation. I have created a powerful tool that based on past technical patterns (volatility, moving averages, statistics, trends, candlesticks, support and resistance, stock index indicators).
All the ones you know (RSI, MACD, STOCH, Bolinger Bands, SMA, DEMARK, Japanese candlesticks, ichimoku, fibonacci, williansR, balance of power, murrey math, etc) and more than 200 others.

The tool creates prediction models of correct trading points (buy signal and sell signal, every stock is good traded in time and direction).
For this I have used big data tools like pandas python, stock technical patterns market libraries like: tablib, TAcharts ,pandas_ta... For data collection and calculation.
And powerful machine-learning libraries such as: Sklearn.RandomForest , Sklearn.GradientBoosting, XGBoost, Google TensorFlow and Google TensorFlow LSTM.

With the models trained with the selection of the best technical indicators, the tool is able to predict trading points (where to buy, where to sell) and send real-time alerts to Telegram or Mail. The points are calculated based on the learning of the correct trading points of the last 2 years (including the change to bear market after the rate hike).

I think it could be useful to you, to improve, I would like to share it with you, and if you are interested in improving and collaborating we could, who knows how to make beautiful things.

Thank you for your time
I'm sorry to contact you here ,by issues, I don't know how I would be able to do it.
mail : [email protected] or https://github.com/Leci37/stocks-Machine-learning-RealTime-telegram/discussions

Here are several improvements I have in my mind, feel free to raise PR and contribute.

- [ ] 1. Make READ.md a web page, make links etc easier to track similar to https://pages.github.com/, this might require a new repo name, so it's not worth the effort, may consider using wiki instead

• 2. Create a data store within the project = data file (csv/pickle) would suffice
• 3. Create python/github api to query tracked project status and retire projects like @firmai suggested
• 4. Somehow allow other users to comment and suggest new inclusions easier (not sure how yet)
• 5. Organize or add extra sections:
  • a. Backtester engines
  • b. Other alternative asset types: crypto on top of my mind, but open to ideas
  • c. Academic scans (might need help with these)
  • d. Quant finance/ml blogs, for example, https://quantocracy.com/

idea is to run get_repo_status() periodically using github action

• - handle github api key - challenge would be to manage the env variable since am not sure github has a secret store
• - schedule it to be ran nightly 2am EST
• - once finished, commit the url_list.csv back to repo master branch if no errors

search api doc
http://developer.github.com/v3/search
search qualifiers details
https://docs.github.com/en/github/searching-for-information-on-github/searching-on-github