Reducing market uncertainty with the adoption of Artificial Intelligence (AI)

[Rogerio Figurelli]

Hello everyone,

The application of Artificial Intelligence (AI) in robots for Forex/Stock Markets/etc. grows more and more, much upon AI hype.

My suggestion is to keep the focus on reducing market uncertainty, as the proposal of this thread.

However, I have received requests regarding Artificial Intelligence applications for HFTs.

And, in that sense, I recommend the following article, with an interesting concept on market microstructure, where we can apply Deep Learning.

Machine Learning for Market Microstructure and High Frequency Trading

http://www.cis.upenn.edu/~mkearns/papers/KearnsNevmyvakaHFTRiskBooks.pdf

"The inference of predictive models from historical data is obviously not new in quantitative finance; ubiquitous examples include coefficient estimation for the CAPM, Fama and French factors, and related approaches. granularity of the data - often microstructure data at the resolution of individual orders, (partial) executions, hidden liquidity, and cancellations - and lack of understanding of how low-level data relates to actionable circumstances (such as profitably buying or selling shares , optimally executing a large order, etc.) In the language of machine learning, such models as CAPM and its variants already prescribe what the relevant variables or "features" are for prediction or modeling (excess returns, book-to-market in many HFT problems one may have no prior intuitions about how (say) the distribution of liquidity in the order book relates to future price movements, if at all. Thus feature selection or feature engineering becomes an important process in machine learning for HFT, and is one of our central themes."

Best,

Rogério Figurelli

[Fernando Carreiro]

Rogerio Figurelli: The application of Artificial Intelligence (AI) in robots for Forex/Stock Markets/etc. grows more and more, much upon AI hype.

My suggestion is to keep the focus on reducing market uncertainty, as the proposal of this thread.

However, I have received requests regarding Artificial Intelligence applications for HFTs.

And, in that sense, I recommend the following article, with an interesting concept on market microstructure, where we can apply Deep Learning.

Machine Learning for Market Microstructure and High Frequency Trading

http://www.cis.upenn.edu/~mkearns/papers/KearnsNevmyvakaHFTRiskBooks.pdf

Thank you for the information! I don't currently use AI in my EAs, but I like keeping apprised on the subject, just in case one day I decide to incorporate such functionality.

[Rogerio Figurelli]

Fernando Carreiro:

Thank you for the information! I don't currently use AI in my EAs, but I like keeping apprised on the subject, just in case one day I decide to incorporate such functionality.

Thanks, Fernando, I believe that, sooner or later, and in one way or another, AI will be present in most EAs.

[Rogerio Figurelli]

Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
http://cs229.stanford.edu/proj2013/TakeuchiLee-ApplyingDeepLearningToEnhanceMomentumTradingStrategiesInStocks.pdf

[Alain Verleyen]

Rogerio Figurelli:

Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks
http://cs229.stanford.edu/proj2013/TakeuchiLee-ApplyingDeepLearningToEnhanceMomentumTradingStrategiesInStocks.pdf

Thanks Rogerio, very interesting topic.

Happy to see you here ;-)

[vaaniseth06]

It was nice information for all traders given by you. I like to also adopt it and try this. we can also get various services from various firms so that we can trade well like best option tips provider in India like forms.

[Rogerio Figurelli]

Alain Verleyen:

Thanks Rogerio, very interesting topic.

Happy to see you here ;-)

Likewise, thanks Alain.

[Rogerio Figurelli]

@vaaniseth06
It was nice information for all traders given by you. I like to also adopt it and try this. we can also get various services from various firms so that we can trade well like best option tips provider in India like forms.

Thank you @vaaniseth06

[Rogerio Figurelli]

AI and productivity J-curve

In my opinion, one of the biggest problems of Artificial Intelligence in the market, for the most varied applications, is related to interpretability. But an interesting and very general concept, which I think is very related to this acceptance, is the productivity J-curve.

https://mitsloan.mit.edu/ideas-made-to-matter/how-machine-learning-can-break-down-language-and-trade-barriers

That’s because there’s typically a significant lag time between the adoption of AI by a company, which involves costly investments, and the delivery of benefits in terms of greater output, the authors wrote. At first, Brynjolfsson said a company’s investment in new AI technology can actually show a decrease in measured productivity, reflecting the initial costs, then later a sharp increase, as the benefits are harvested. He calls this phenomenon he calls the “productivity J-curve.”

The Productivity J-Curve: How Intangibles Complement General Purpose Technologies

https://economics.stanford.edu/sites/g/files/sbiybj9386/f/brynrocksyv_j-curve_final.pdf

"We call this phenomenon the Productivity J-Curve. As firms adopt a new GPT, total factor

productivity growth will initially be underestimated because capital and labor are spent to accumulate

unmeasured intangible capital stocks. Later, measured productivity growth overestimates true

productivity growth because the capital service flows from those hidden intangible stocks generates

measurable output. The error in measured total factor productivity therefore follows a J-curve shape,

initially dipping while the investment rate in unmeasured capital is larger than the investment rate in

other types of capital, then rising as growing intangible stocks begin to affect measured production."

[Farrukh Aleem]

Nice sharing i will study your links.

[Rogerio Figurelli]

Farrukh Aleem:
Nice sharing i will study your links.

Thank you Farrukh, you are welcome.