Quantitative Asset Allocation: Factors, Trend Following and More
Between mind and machine
Recently, discussions of whether the AI-based ChatGPT can be successfully used to place trades have been spreading among the investment community. The core of the debate is however not new: can machines beat human allocators in generating alpha? Recent developments seem to suggest that machines may be better than the human mind. However, investors can form their own views on this matter by engaging with the content below.
Faster trend-following strategies offer an appealing risk-reward profile for investors looking at novel ways of generating alpha.
Quantitative analysis focuses on data. This is in contrast with fundamental analysis that enables investors to rely on what they think the future holds.
This paper provides a new momentum factor model which takes into account the entirety of the data set, rather than just the first and last points.
The research shows that due to the reversal of price pressures, flow-induced demand in the size and value factors negatively predicts factor returns.
领英推荐
Multi-factor strategies are currently trading at cheap valuations, offering attractive upside potential to investors looking at quant-based allocations.
There are many different machine learning models that can be used in trading, all offering different benefits and drawbacks to investors.
The conclusion of this paper is that export indexes capture trends in real exports and compare favourably with existing statistics.
How do different factors perform during various market cycles? This paper looks at how Quantpedia's Multi-Factor Regression Model delivered during these periods of time.
By:?Anton Balint,?Senior Investment Writer