Why financial machine learning hasn’t kept up

Photo by Rock'n Roll Monkey on Unsplash

In recent times, thanks to developments in both research and computation power, we have seen vast advances in the field of machine learning with applications spanning fields such as e-commerce, manufacturing and transportation. So much so that in some narrow cases AI has been shown to exceed even human capabilities. Intuitively, it stands to reason that the investors big and small alike should also be beneficiary to this trend as the environment is rich with data and the mere mention of stocks is enough to conjure up mental images of price charts ripe with hidden patterns.

However this has not…


And Why It’s Not a Bad Thing

Photo by Levi Bare on Unsplash

As advances in AI continue to progress in leaps and bounds, accessibility to data science at a base level has become increasingly democratized. Traditional entry barriers to the field such as a lack of data and computing power have been swept aside with a continuous supply of new data startups popping up(some offering access for as little as a cup of coffee a day) and all powerful cloud computing removing the need for expensive onsite hardware. Rounding out the trinity of prerequisites, is the skill and know-how to implement, which has arguably become the most ubiquitous aspect of data science…


Obstacles That Challenge Its Acceptance

Photo by Tim Marshall on Unsplash

As the price of Bitcoin surged to yet another all time high, crypto-mania has truly taken hold as seasoned hedge fund investors have signaled their openness to allocating to the digital currency while JP Morgan has presented long-term forecasts as high as $146,000. Despite the renewed enthusiasm that accompanied Bitcoin’s 2020 rally, it’s acceptance as a mainstream asset relies on much more than speculation and narrative. …


A Retrospection

Photo by Igor Kasalovic on Unsplash

As each year draws to a close, it is often customary to take the time to reflect on some of the more memorable moments that have come to pass before looking forward to the next one. While 2020 will be deemed as a year to forget by many it will undoubtedly be remembered by history. From COVID19 and Black Lives Matter movement, to Megxit, this article aims to briefly summarize and visualize (in no particular order) some of the key social, economical and cultural events that have come to define the year that was 2020.

COVID19


And Why the Dividend Investing Narrative is Misleading

Photo by Conor Luddy on Unsplash

The concept of passive income has become an increasingly popular topic of late. After all, who doesn’t want to learn about making easy money? But what began as a tax label to classify income other than that derived from employment has now become synonymous with any endeavor that can easily and consistently generate income. However, therein lies the problem, there’s no such thing as a free lunch. Economic 101 dictates that whenever there is an opportunity that arises from a disequilibrium, market forces will move in such a way to exploit it till it is arbitraged away. …


Artificial Intelligence, Opinion

Resources for the Data Minded Investor

Photo by Susan Yin on Unsplash

As AI and machine learning have regained popularity over the last two decades, so has an interest in their application to financial prediction tasks. The two seem like a natural fit as data generated by markets have been scrutinized by investors for over a century in hopes of forecasting their way to financial success. A casual survey of the associated literature reveals there are generally two broad approaches to the topic. In one corner sits the astute STEM practitioners who view the task at hand as an engineering problem, preferring complex and novel architectures that minimize a nominated error metric…


A Breakdown of a Timeless Investing Metric

Photo by Jaredd Craig on Unsplash

Since the popularization of value investing by Benjamin Graham in “The Intelligent Investor” (and Security Analysis) the price earnings ratio(PE) has been a favorite among investors to help gauge the valuation of stocks. While its does provide a simple and easy to understand metric, its use can be subjective and bound by nuance. The below post aims to offer a quick and intuitive guide to how PE can be used to guide investing.

Price vs Valuation

While the two concepts are invariably linked, a high price does not immediate imply a high valuation. Outside of market forces, the absolute price of a stock…


Machine Learning, Probability

And Why Randomness is Not Your Friend

Photo by Andrea Ferrario on Unsplash

While 2020 has been deemed as a year to forget by many, it is undeniable that it will be remembered by history. As much of the world slipped into a COVID19 induced recession, the markets recovered from a brief stumble to return to its previous upward trajectory, one that has been predicated by a decade long bull market lead by the tech sector. …


What to consider before embarking on one

Photo by Patrick Tomasso on Unsplash

With the resurgence of machine learning and artificial intelligence, never has it been easier to implement predictive algorithms both new and old. With just a few lines of code, state of the art models can be readily accessible at the fingertips of the budding data enthusiast, ready to conquer whatever insurmountable digital task may lay at hand. But a little bit of knowledge can be a dangerous thing. While much of machine learning can be attributed to statistics and programming what is equally important, but often skipped over in favor of instant gratification, is domain knowledge.

Nowhere is this more…


A Python Implementation

Photo by Fahrul Azmi on Unsplash

In recent years we have seen vast advances in the field of computer vision, the application of which spans many industries. Convolutional Neural Networks (CNN) have come to be known as the pre-eminent method in image classification as evidenced by its success in the ImageNet Large Scale Visual Recognition Challenge, and in some narrow cases have even reportedly exceeded human abilities. Although in this post we will explore a similar problem, we will approach it with the much simpler K-Nearest Neighbor(KNN) algorithm and in doing so show that reasonable performance can still be achieved with a less complex classifier. …

Mikhail Mew

Researcher | Investor | Data Scientist | Curious Observer. Thoughts and insights from the confluence of investing and machine learning.

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