Research axes

All the research topics covered by the QMI are structured around the 3 main stages of the creation of a quantitative investment strategy. The first step is related to signal generation. Particular attention will be paid to the use of artificial intelligence in this production of signals. The second step involves portfolio construction and dynamic risk management. In particular, we are interested in the optimal use of techniques from the world of derivatives. Issues related to potential crowding due to joint use of related strategies by different funds will also be addressed. Finally, the last step covers all the challenges of real-world implementation of paper portfolios from the previous step.

Amongst the research areas of most interest to the QMI for 2017 we had:

1. Artificial Intelligence

Statistical Signal Processing

Application of signal treatment to the estimation of factorial models, the detection of outliers, the filtering of trends and the robust estimation of Kalman models is an active research field of the IdR QMI. The robust Kalman filter is in particular used in a project aiming to filter the leverage of Real Estate Private Equity funds form reported NAV. These funds are reporting on a quarterly basis, and the use of classic Kalman filter produces in general poor results in this specific context.

Big data, machine learning and the new sources of information (Google, Twitter)

The University of Rotterdam’s project (mentioned above) also relates to this theme. A paper on the statistical analysis of big data has been presented at several international conferences by Christian Gouriéroux. This has been published in Journal of Econometrics in 2017 (See Publications). QMI organized a workshop on “Big Data: A revolution for financial markets and the asset management industry?” in March 2017.

Momentum risk premia

Serge Darolles is working with his PhD Student Charles Chevalier on the characterization of a Multi-asset Trend Following Risk Premia that can be used to explain the cross sectional dispersion observed in the CTA space. The corresponding risk factor can be used to improve the explanatory power of the linear factor models generally used to analyse hedge fund portfolios.
 

2. Risk & Crowding

Risk disaggregation and portfolio allocation

A change in the structure of a fund's client base affects the potential mismatch between the liquidity of its assets and liabilities. An asset/liability approach for liquidity management is therefore critical and requires a client behaviour model. Serges Darolles and Gaëlle Le Fol are working with some co-authors on investor’s behaviour and the consequences on funding liquidity risk. This research has been presented at several seminars and international conferences.
Emmanuel Jurczenko has published the third volume of the QuantValley collection, published with Elsevier, on Factor Investing in 2017 (See Books release). Each chapter deals with new methods for constructing and harvesting traditional and alternative risk premia, building strategic and tactical multifactor portfolios. This research has been encouraged by QMI and presented at a QMI Workshop in London in November 2017 (See Workshops).

Contagion and funds flows

Mardi Dungey and Eric Renault have also received funding of 10,000 euros by the QMI for their project on contagion modelling (See Recently Funded and Completed projects). Identifying contagion effects during periods of financial crisis is known to be complicated by the changing volatility of asset returns during periods of stress. To untangle this, they propose a GARCH (generalized autoregressive conditional heteroskedasticity) common features approach, where systemic risk emerges from a common factor source (or indeed multiple factor sources) with contagion evident through possible changes in the factor loadings relating to the common factor(s). This research has now been published in Journal of Applied Econometrics in 2017 (See Publications).

 3. Implementation challenges

Listed market liquidity

Serge Darolles, Gaëlle Le Fol and Gulten Mero are working on dynamics measures of short-term and long-term liquidity measures based on the autocorrelation of return, volume and volatility. This research has been published in Journal of Econometrics 2017 (See Publications).
Taking another look at serial correlations, Serge Darolles and Gaëlle Le Fol with another co-author are working on hedge funds liquidity and managers’ skills (See Working Papers 2017).
Gaëlle Le Fol is also leading a new project that focuses on multivariate models to analyse the liquidity structure of a large panel of assets. Serge Darolles, Béatrice Sagna – PhD student under Gaëlle Le Fol’s supervision and Christian Brownlees from Pompeu Fabra are part of that project. Fabrice Riva is for his part, with two co-authors, working on ETF liquidity (See Working papers 2017).
A « Contributions in Liquidity » session leaded by Gaëlle Le Fol, Member of the QMI has been organised at the Computational Financial Econometrics (CFE) conference in London in December 2017 (see past conferences). During the same conference, several papers were also presented in the « Quantitative Investing » session organised by Serge Darolles, Member of the QMI. This session focused on the impact of liquidity in the design of investment strategies and portfolio allocation tools (See Other conferences).

Algo and/or High frequency trading

Optimisation of the VWAP (Volume Weighted Average Price) replication algorithms, link between the speed of placing orders on the market and the arrival of information, liquidity trade-offs, maximum trading capacity.
Algo and High frequency trading defenders say that they provide liquidity and improve price efficiency. Serge Darolles, Gaëlle Le Fol and Gulten Mero, in a paper published in Journal of Econometrics, show that investors are acting strategically – by slicing their orders - to avoid being picked-off by HFTs. Doing so, they slow down the propagation of information in the prices. Again, this research has been presented several times in international conferences (see Annual report 2017).