Momentum stocks have a bimodal distribution in the US market, i.e., winners tend to become losers and vice versa. We investigate the existence of bimodality and the profitability of deep momentum, a machine learning return prediction model designed to address bimodality, in the UK, Japan, China,...

Machine learning techniques have gained enormously in popularity in recent years, but so far only to a very limited extent in fixed income research. In this paper we therefore like to do some pioneering work and apply Boosted Regression Trees to Equity Momentum in the corporate bond market. We...

We examine the effectiveness of applying a trend following methodology to global asset allocation between equities, bonds, commodities and real estate. The application of trend following offers a substantial improvement in risk-adjusted performance compared to traditional buy-and-hold...

This paper studies intraday time-series momentum (ITSM) in an international setting by employing high-frequency data of 16 developed markets. We show that ITSM is economically sizable and statistically significant both in- and out-of-sample in most countries. Based on existing theories of...

Motivated by studies of the impact of frictions on asset prices, we examine the effect of key components of time-series momentum strategies on turnover and performance. We show that more efficient volatility estimation and price trend detection can significantly reduce portfolio turnover by more...

This study decomposes a momentum factor (MOM) in the commodity futures market. A high-to-price (HTP) factor generates a higher Sharpe ratio than a price-to-high (PTH) factor. We uncover that the profitability mechanisms across three momentum factors are different. The positive returns on MOM and...

We study the well-known multiplicative Lognormal cascade process in which the multiplication of Gaussian and Lognormally distributed random variables yields time series with intermittent bursts of activity. Due to the non-stationarity of this process and the combinatorial nature of such a...

We study the well-known multiplicative Lognormal cascade process in which the multiplication of Gaussian and Lognormally distributed random variables yields time series with intermittent bursts of activity. Due to the non-stationarity of this process and the combinatorial nature of such a...

High momentum returns cannot be explained by risk factors, but they are negatively skewed and subject to occasional severe crashes. I explore the timing of momentum crashes and show that momentum strategies tend to crash in 1-3 months after the local stock market plunge. Next, I propose a simple...

We show that stock prices underreact when there is a political event, reflected in higher momentum returns. We conjecture that political news crowds out stock news cause investors to distract, trade more indexes and underreact to firm specific news. We analyze momentum returns following general...