Co-founder of consulting firm Neurons Lab, author of applied ML courses. On Medium, I write about proven strategies for achieving ML technology leadership.
Image for post
Image for post
Wave motion illustration http://animatedphysics.com/insights/modelling-photon-phase/

In the previous article, we have built experiments where we have learned how to approximate physical laws models with machine learning algorithms, which was a preamble for a “real” data generation process. In this article, we won’t simply approximate the dependency between a time step and the exact position of the object but will generate whole trajectories as objects coming from a data distribution and will try to control this process and the variables as we do in classic mathematical models.

This article concludes the idea of the evolution of mathematical modeling from human-designed first to data-driven first and I hope, it will clarify why we need generative modeling today and you will be able to implement it in your R&D and product activities. …


Image for post
Image for post
Wave motion illustration http://animatedphysics.com/insights/modelling-photon-phase/

GANs and other generative machine learning algorithms are still hyped and work fantastically with images, texts, and sounds. They’re able not only to generate data for fun but solve important theoretical issues and boost production ML pipelines. Unfortunately, typical today’s practical use case is limited to “fine-tune pre-trained StyleGAN2 for zombies generation”. And what’s worse, almost no one cares to explain why do we need generative modeling in the real world and where the roots of such need are coming from.

The following two articles aim to bridge the gap between modern cool stuff and slightly forgotten old-school mathematical modeling, where there were no big datasets and powerful neural networks. …


SIMULATIONS, RISKS, AND METRICS

Understanding strategy risk and the probability of overfitting: small numbers that change everything

Image for post
Image for post
Illustration from https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3544431

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

This is the third and the last article in a short series about “how to believe the backtests”. We have started with an overview of classic metrics for risk and reward and expanded them with new ones that tell more not only about the PnL curve itself but about underlying data, models, fat-tails, and corrections for multiple experiments. It could give us more understanding about a single backtest, but still, if this backtest is characterized by a single realization of a stochastic process, it is not worth much. That’s why in the second article we focused on different ways to produce multiple backtests from a single piece of the data: cross-validations, simulations, and scenarios. …


SIMULATIONS, RISKS, AND METRICS

Combinatorial and scenario-based backtesting from historical data and simulations

Image for post
Image for post
Illustration from https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3544431

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

Let’s disassemble backtests and make them great again :) In the previous part, we have reviewed the main dangers of the classic backtesting routine with the historical data and standard metrics related to the strategy performance. …


SIMULATIONS, RISKS, AND METRICS

On the dangers of walk-forward backtesting, how to measure them and not feel right, but to be right

Image for post
Image for post
Illustration form https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3544431

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

Quantitative research is a process with many intermediate steps, each of which has to be carefully and thoroughly validated. Asset selection, data collection, feature extraction, modeling — all these phases take time and are delivered and tested by different teams. But what at the end the investor wants to see? That “flawless” backtest on historical data with high Sharpe ratio, alpha with respect to the market, and maybe some fund-related metrics as capacity, leverage, average AUM, etc. …


Coding or selling the code?

Disassembling careers of the technology rockstars and young entrepreneurs all over the world

Image for post
Image for post
https://www.scmp.com/magazines/style/tech-design/article/3023666/9-mind-blowing-tech-predictions-steve-jobs-bill-gates

There are two topics that are covered in a veil of secrecy, myths, and misunderstandings. They keep busy the minds of most people not depending on the circumstances. We are making life-changing decisions just to get these two things in one or another way. These things are sex and money. I hope that with the first one you’re happy and satisfied, so in this article, I’d like to focus on the latter, in particular, the main way of accumulating wealth: building a successful career through improving skills, promotions, publicity, and other moves. My thoughts will be based on biographies of well-known entrepreneurs, my own experience of moving from an employed data scientist to the tech entrepreneur and success and failure stories, of my colleagues and of my friends from A-Players, that help tech specialists to grow as managers and entrepreneurs. …


Right impact at the right time

Datasets and R&D directions for today’s pandemic and future public security

Image for post
Image for post
https://www.cdc.gov/coronavirus/2019-ncov/index.html

During the last couple of months, the COVID-19 outbreak more known as “coronavirus” or “Wuhan” was the most discussed topic online and on the empty streets. We had different opinions about it from conspiracy theories to comparisons with regular influenza, but today we are in front of a fact that COVID-19 is a pandemic and somehow we need to protect from it, stop its spreading and, finally, fight it.

As a person, who works in the AI field, in this blog, I’d like to share some directions where I and my colleagues can work to help public and private sectors all over the world. I hope that entrepreneurs and members of the government will see the opportunities not only for the temporary getting rich schemes or control of the citizens but as important parts of a strategical roadmap to improving public health and security. …


Feature importance: a financial research driver that won’t let you down

Image for post
Image for post
https://blog.darwinex.com/wp-content/uploads/2018/11/backtest-darwins-en-1030x426.png

How do we usually do trading ideas research? We get some data with the hope of having some predictive value there, prepare it, extract potential alphas, train forecasting models to predict prices based on that alphas and after run some long-short strategy backtest based on the trained model. If it looks good, we are happy to invest our money there. Looks pretty legit, right? Although, not everyone agrees with it.


Nature vs Von Neumann vs Neural networks

A story on reproduction in biology, machines, and AI

Image for post
Image for post
https://en.wikipedia.org/wiki/Self-replicating_machine

We are already used to see the impact of AI everywhere around us not just in digital life (from recommendations on Netflix to voice recognition by Siri and Alex) but also in physical: Amazon Go, CCTV surveillance and taxis without drivers and it indeed made our lives better. What is a bit disappointing, that the “intelligence” doesn’t seem anything like a human or even biological intelligence, because it is just a set of mathematical models that have been fit their degrees of freedom based on some empirical observations. What do we expect from the intelligent creature? Apart from the raw intelligence, it could probably sense of humor, compassion, ability to interpret its own decisions and, of course, the ability to reproduce. Everything but the latter point was already successfully implemented in some algorithmic form, that’s why this article will focus on trying to build such AI (an artificial neural network here) that is able to copy itself, i.e. …


Optimization? Learning? Control?

The evolution of quantitative asset management techniques with empirical evaluation and Python source code

Image for post
Image for post
This is how we’d like them to grow https://investresolve.com/blog/category/diversification/

Artificial intelligence, machine learning, big data, and other buzzwords are disrupting decision making in almost any area of finance. On the back office, machine learning is widely applied to spot anomalies in execution logs, for risk management and fraudulent transaction detection. At the front office, AI is used for customer segmentation and support and pricing the derivatives.

But of course, the most interesting applications of AI in finance are in the buy-side and are related to searching the predictive signal in the noise and catching that alpha. …

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store