Evaluating macro trading signals in three simple steps

Jupyter Notebook

Meaningful evaluation of macro trading signals must consider their seasonality and diversity across countries. This post proposes a three-step process to this end. The first step runs significance tests of proposed predictive relations using a panel of markets. The second step reviews the reliability of predictive relations based on accuracy and different correlation metrics across time and markets. The third step estimates the economic value of the signal based on performance metrics of a standardized naïve PnL. All these steps can be implemented with special Python classes of the Macrosynergy package. Conscientious evaluation of macro signals not only benefits their selection for live trading. It also paints a realistic picture of the PnL profile, which is critical for setting risk limits and for broader portfolio integration.

(more…)

Equity market timing: the value of consumption data

Jupyter Notebook

The dividend discount model suggests that stock prices are negatively related to expected real interest rates and positively to earnings growth. The economic position of households or consumers influences both. Consumer strength spurs demand and exerts price pressure, thus pushing up real policy rate expectations. Meanwhile, tight labor markets and high wage growth shift national income from capital to labor.
This post calculates a point-in-time score of consumer strength for 16 countries over almost three decades based on excess private consumption growth, import trends, wage growth, unemployment rates, and employment gains. This consumer strength score and most of its constituents displayed highly significant negative predictive power with regard to equity index returns. Value generation in a simple equity timing model has been material, albeit concentrated on business cycles’ early and late stages.

(more…)

Optimizing macro trading signals – A practical introduction

Jupyter Notebook

Based on theory and empirical evidence, point-in-time indicators of macroeconomic trends and states are strong candidates for trading signals. A key challenge is to select and condense them into a single signal. The simplest (and often successful) approach is conceptual risk parity, i.e., an equally weighted average of normalized scores. However, there is scope for optimization. Statistical learning offers methods for sequentially choosing the best model class and other hyperparameters for signal generation, thus supporting realistic backtests and automated operation of strategies.
This post and an attached Jupyter Notebook show implementations of sequential signal optimization with the scikit-learn package and some specialized extensions. In particular, the post applies statistical learning to sequential optimization of three important tasks: feature selection, return prediction, and market regime classification.

(more…)

Sovereign debt sustainability and CDS returns

Selling protection through credit default swaps is akin to writing put options on sovereign default. Together with tenuous market liquidity, this explains the negative skew and heavy fat tails of generic CDS (short protection or long credit) returns. Since default risk depends critically on sovereign debt dynamics, point-in-time metrics of general government debt sustainability for given market conditions are plausible trading indicators for sovereign CDS markets and do justice to the non-linearity of returns. There is strong evidence of a negative relation between increases in predicted debt ratios and concurrent returns. There is also evidence of a negative predictive relation between debt ratio changes and subsequent CDS returns. Trading these seems to produce modest but consistent alpha.

(more…)

How to measure the quality of a trading signal

The quality of a trading signal depends on its ability to predict future target returns and to generate material economic value when applied to positioning. Statistical metrics of these two properties are related but not identical. Empirical evidence must support both. Moreover, there are alternative criteria for predictive power and economic trading value, which are summarized in this post. The right choice depends on the characteristics of the trading signal and the objective of the strategy. Each strategy calls for a bespoke appropriate criterion function. This is particularly important for statistical learning that seeks to optimize hyperparameters of trading models and derive meaningful backtests.

(more…)

Nowcasting macro trends with machine learning

Nowcasting economic trends can make use of a broad range of machine learning methods. This not only serves the purpose of optimization but also allows replication of past information states of the market and supports realistic backtesting. A practical framework for modern nowcasting is the three-step approach of (1) variable pre-selection, (2) orthogonalized factor formation, and (3) regression-based prediction. Various methods can be applied at each step, in accordance with the nature of the task. For example, pre-selection can be based on sure independence screening, t-stat-based selection, least-angle regression, or Bayesian moving averaging. Predictive models include many non-linear models, such as Markov switching models, quantile regression, random forests, gradient boosting, macroeconomic random forests, and linear gradient boosting. There is some evidence that linear regression-based methods outperform random forests in the field of macroeconomics.

(more…)

Macroeconomic cycles and asset class returns

Jupyter Notebook

Indicators of growth and inflation cycles are plausible and successful predictors of asset class returns. For proof of concept, we propose a single balanced “cyclical strength score” based on point-in-time quantamental indicators of excess GDP growth, labor market tightening, and excess inflation. It has clear theoretical implications for all major asset markets, as rising operating rates and consumer price pressure raise real discount factors. Empirically, the cyclical strength score has displayed significant predictive power for equity, FX, and fixed income returns, as well as relative asset class positions. The direction of relationships has been in accordance with standard economic theory. Predictive power can be explained by rational inattention. Naïve PnLs based on cyclical strength scores have each produced long-term Sharpe ratios between 0.4 and 1 with little correlation with risk benchmarks. This suggests that a single indicator of cyclical economic strength can be the basis of a diversified portfolio.

(more…)

Rational inattention and trading strategies

The theory of rational inattention supports the development of trading strategies by providing a model of how market participants manage the scarcity of attention. In general, people cannot continuously process and act upon all information, but they can set priorities and choose the mistakes they are willing to accept. Rational inattention explains why agents pay disproportionate attention to popular variables, simplify the world into a small set of indicators, pay more attention in times of uncertainty, and limit their range of actions. In macroeconomics, rational inattention elucidates why forecasters underreact to shocks and why pure nominal variables, such as money and interest rates have persistent real effects. In finance, rational inattention explains why markets ignore a wide range of relevant data, leave pockets of information advantage, exaggerate price volatility, and propagate financial contagion.

(more…)

Excess inflation and asset class returns

Jupyter Notebook

Excess inflation means consumer price trends over and above the inflation target. In a credible inflation targeting regime, positive excess inflation skews the balance of risks of monetary policy towards tightening. An inflation shortfall tips the risk balance towards easing. Assuming that these shifting balances are not always fully priced by the market, excess inflation in a local currency area should negatively predict local rates market and equity market returns, and positively local-currency FX returns. Indeed, these hypotheses are strongly supported by empirical evidence for 10 developed markets since 2000. For fixed income and FX excess inflation has not just been a directional but also a relative cross-country trading signal. The deployment of excess inflation as a trading signal across asset classes has added notable economic value.

(more…)

Macro factors of the risk-parity trade

Risk-parity positioning in equity and (fixed income) duration has been a popular and successful investment strategy in past decades. However, part of that success is owed to a supportive macro environment, with accommodative refinancing conditions and slow, disinflationary, or even deflationary economies. Financial and economic shocks, as opposed to inflation shocks, dominated markets, leading to a negative equity-duration correlation. The macro environment is changeable, however, and a strong theoretical case can be made for managing risk-parity strategies based on economic trends and risk-adjusted carry. We propose simple strategies based on macro-quantamental indicators of economic overheating. Overheating scores have been strongly correlated with risk parity performance and macro-based management would have even benefited risk parity performance even during the past two “golden decades” of risk parity.

(more…)