Does the investment in sophisticated machine learning algorithm research and development pay off? It is an important question, especially in light of the increasing costs related to the R&D of such algorithms and the possibility of decreasing returns for some methods developed in the more distant past. A recent paper by Azevedo, Hoegner, and Velikov (2023) evaluates the expected returns of machine learning-based trading strategies by considering transaction costs, post-publication decay, and the current high liquidity environment. The obstacles are not low, but research suggests that despite high turnover rates, some machine learning strategies continue to yield positive net returns.

The area we want to explore today is an interesting intersection between quantitative and more technical approaches to trading that employ intuition and experience in strictly data-driven decision-making (completely omitting any fundamental analysis!). Can just years of screen time and trading experience improve the metrics and profitability of trading systems through discretionary trading actions and decisions?

It is not easy to build a robust trend-following strategy that will withstand different difficult market conditions and bring consistent results. The author of today’s work was not frightened by this task and delivered a full framework on how to design a robust trend-following strategy step by step.

Hello all,

What have we accomplished in the last month?

– A new Attribution Analysis report for Quantpedia Pro clients
– An exclusive promo from QuantInsti
– 11 new Quantpedia Premium strategies have been added to our database
– 8 new related research papers have been included in existing Premium strategies during the last month
– Additionally, we have produced 7 new backtests written in QuantConnect code
– 5 new blog posts that you may find interesting have been published on our Quantpedia blog in the previous month

There exist two most common techniques for constructing multifactor portfolios. The mixing approach creates single-factor portfolios and then invests proportionally in each to build a multifactor portfolio. The integrated approach combines single-factor signals into a multifactor signal and then constructs a multifactor portfolio based on that multifactor signal. Which methodology is better? It is hard to tell, and numerous papers show each method’s pros and cons. The recent paper from Joris Blonk and Philip Messow explores this question from the standpoint of the credit fixed-income portfolio manager and offers their analysis, which shows that an integrated approach is probably better in this particular asset class.

One of the main reasons why the Pragmatic Asset Allocation Model was designed is to give investors a tax-efficient possibility to invest in a global equity portfolio with a lower risk than the passive buy&hold approach. Therefore, the PAA model is not the “absolute return” model but rather the tactical model that prefers to invest in the equity risk premium and move to the hedging portfolio (gold, treasuries, or cash), only for short periods and only when it’s absolutely necessary. We use price trend+momentum indicators and yield curve inversion as signals for such situations when (based on the past data) there is a higher probability of recessions and equity bear markets. What is unusual in the current situation is the length of time that the YC is inverted (19 months at the moment), which makes it the 2nd longest YC inversion in the last 100 years, and we are analyzing the implications for the PAA model.