Ten things investors should know about nowcasting

September 4, 2021

Nowcasting in financial markets is mainly about forecasting forthcoming data reports, particularly GDP releases. However, nowcasting models are more versatile and can be used for a range of market-relevant information, including inflation, sentiment, weather, and harvest conditions. Nowcasting is about information efficiency and is particularly suitable for dealing with big messy data. The underlying models typically condense large datasets into a few underlying factors. They also tackle mixed frequencies of time series and missing data. The most popular model class for nowcasting is factor models: there are different categories of these that produce different results. One size does not fit all purposes. Also, factor models have competitors in the nowcasting space, such as Bayesian vector autoregression, MIDAS models and bridge regressions. The reason why investors should understand their nowcasting models is that they can do a lot more than just nowcasting: most models allow tracking latent trends, spotting significant changes in market conditions, and quantifying the relevance of different data releases.

(more…)

Macro trends for trading models

August 21, 2021

Unlike market price trends, macroeconomic trends are hard to track in real-time. Conventional econometric models are immutable and not backtestable for algorithmic trading. That is because they are built with hindsight and do not aim to replicate perceived economic trends of the past (even if their parameters are sequentially updated). Fortunately, the rise of machine learning breathes new life into econometrics for trading. A practical approach is “two-stage supervised learning”. The first stage is scouting features, by applying an elastic net algorithm to available data sets during the regular release cycle, which identifies competitive features based on timelines and predictive power. Sequential scouting gives feature vintages. The second stage evaluates various candidate models based on the concurrent feature vintages and selects at any point in time one with the best historic predictive power. Sequential evaluation gives data vintages. Trends calculated based on these data vintages are valid backtestable contributors to trading signals.

(more…)

Machine learning for portfolio diversification

August 7, 2021

Dimension reduction methods of machine learning are suited for detecting latent factors of a broad set of asset prices. These factors can then be used to improve estimates of the covariance structure of price changes and – by extension – to improve the construction of a well-diversified minimum variance portfolio. Methods for dimension reduction include sparse principal components analysis, sparse partial least squares, and autoencoders. Both static and dynamic factor models can be built. Hyperparameters tuning can proceed in rolling training and validation samples. Empirical analysis suggests that that machine learning adds value to factor-based asset allocation in the equity market. Investors with moderate or conservative risk preferences would realize significant utility gains.

(more…)

Accounting data as investment factors

July 24, 2021

Corporate balance sheet data are important building blocks of quantitative-fundamental (“quantamental”) investment factors. However, accounting terms are easily misunderstood and confused with economic concepts. Accounting is as much driven by assessment of risk as it is by economic value. For example, earnings are recognized only when receipt of cash is highly certain. Investment spending is recognized as such only when there is a high probability of related payoffs. Acknowledging links to risk and the double-entry system, accounting data can be combined into factors that capture the information that they jointly convey. For example, earnings yields become a more meaningful indicator when also considering return on equity and expended investment ratios.

(more…)

Diversified reward-risk parity

July 10, 2021

Risk parity is a portfolio construction technique that seeks to equalize risk contributions from the different components of the portfolio. Risk parity with respect to uncorrelated risk sources maximizes diversification. Simple risk parity rules are based on the inverses of market beta, price standard deviation, or price variance. These methods can be combined with common reward risk metrics, such as the Sharpe ratio, Calmar ratio, STAR ratio, or Rachev ratio. The resulting diversified reward-risk parity allocations have not only outperformed equally-weighted risk portfolios and standard factor allocations but also provided enhanced risk management.

(more…)

A market-to-book formula for equity strategies

June 26, 2021

A new proxy formula for equity market-to-book ratios suggests that (the logarithm of) such a ratio is equal to the discounted expected value of (i) differences between return on equity and market returns and (ii) the net value added from share issuance or repurchases. A firm with a higher market-to-book ratio must have lower future returns, higher return on equity, or more valuable growth or repurchase opportunities. One can cleanly decompose return forecasts into forecasts of future profitability, investment, and the market-to-book ratio at any horizon. Empirical evidence confirms that market-to-book ratios predict returns in the long run, but only to the extent that the ratio itself is not affected by profitability and investment. Indeed, profitability and investment value-added jointly explain about 60% of variations in market-to-book ratio and – hence – should be taken into consideration for investment strategies based on valuation ratios. This broader view helps to forecast returns on value stocks versus growth stocks.

(more…)

Markets’ neglect of macro news

June 12, 2021

Empirical evidence suggests that investors pay less attention to macroeconomic news when market sentiment is positive. Market responses to economic data surprises have historically been muted in high sentiment periods. Behavioral research supports the idea that investors prefer heuristic decision-making and neglect fundamental information in bullish markets, but pay more attention in turbulent times. This allows prices to diverge temporarily from fundamentals and undermines the conventional risk-return trade-off when sentiment is high. Low-risk portfolios tend to outperform subsequently. The sentiment bias also means that fundamental predictors of market prices work better in low-sentiment periods than in high-sentiment periods.

(more…)

Factor momentum: a brief introduction

May 29, 2021

Standard equity factors are autocorrelated. Hence, it is not surprising that factor strategies have also displayed momentum: past returns have historically predicted future returns. Indeed, factor momentum seems to explain all return momentum in individual stocks and across industries. Momentum has been concentrated on a subset of factors, most notably those related to “betting against beta”, a leveraged strategy that is long high-beta stocks and short low beta stocks. Also, factor return autocorrelation has been changing over time. Measures of continuation in factor returns can indicate “momentum crashes”. A plausible cause of factor momentum is mispricing, i.e. drifts of prices in accordance with fundamental gravity, if positions that exploit the mispricing bear systematic risk.

(more…)

The macro forces behind equity-bond price correlation

May 15, 2021

Since the late 1990s, the negative price correlation of equity and high-grade bonds has reduced the volatility of balanced portfolios and boosted Sharpe ratios of leveraged “long-long” equity-bond strategies. However, this correlation is not structurally stable. Over the past 150 years, equity-bond correlation has changed repeatedly. A structural economic model helps to explain and predict these changes. The key factor is the dominant macro policy. In an active monetary policy regime, where central bank rates respond disproportionately to inflation changes, the influence of technology (supply) shocks dominates markets and the correlation turns positive. In a fiscal policy regime, where governments use debt financing to manage the economy, the influence of investment (financial) shocks dominates and the correlation turns negative. In a world with low inflation and real interest rates, the fiscal regime is typically more prevalent.

(more…)

Macro information waste and the quantamental solution

May 1, 2021

Financial markets are not macro information efficient. This means that investment decisions miss out on ample relevant macroeconomic data and facts. Information goes to waste due to research costs, trading restrictions, and external effects. Evidence of macro information inefficiency includes sluggishness of position changes, the popularity of simple investment rules, and the prevalence of herding.  A simple and practical enhancement of macro information efficiency is the construction of quantamental indicators. A quantamental indicator is a time series that represents the state of an investment-relevant fundamental feature in real-time. The term ‘fundamental’ means that these data inform directly on economic activity, unlike market prices, which inform only indirectly. The key benefits of quantamental indicators are that [1] they fit machine learning pipelines and algorithmic trading tools, thus making a broad set of macro information tradable, [2] they support the consistent use of macro information, [3] they can be applied across traders (or programs), strategy types and asset classes and are, thus, cost-efficient.

(more…)

Tags

Tags
asset management Asset Purchase Program banks bond returns bond yields bubbles capital regulation carry China collateral commodities credit returns default ECB economic data EM equity returns euro area crisis Fed financial crisis FX FX interventions FX returns government debt government deficits herding inflation information insurances Japan leverage liquidity machine learning market turmoil price factors regulation risk management shadow banking statistical methods term structure trend following variance risk premium VIX volatility ZLB
ABOUT US

Macrosynergy is a London based macroeconomic research and technology company whose founders have developed and employed macro quantamental investment strategies in liquid, tradable asset classes, across many markets and for a variety of different factors to generate competitive, uncorrelated investment returns for institutional investors for two decades. Our quantitative-fundamental (quantamental) computing system tracks a broad range of real-time macroeconomic trends in developed and emerging countries, transforming them into macro systematic quantamental investment strategies. In June 2020 Macrosynergy and J.P. Morgan started a collaboration to scale the quantamental system and to popularize tradable economics across financial markets.

FOLLOW US
Linkedin
LEGAL
Research
Quantamental Academy
About Us