The project aims to investigate the effect of ESG scores on stock returns and riskmeasures. The research will explore different deep-learning tools to model complexmultivariate time-series data. Deep Neural Networks can infer high-order correlationsin complex data with large volumes and dimensionality. Researchers have developedseveral models to improve the performance of DNN-based methods, including CCN,TCN, LSTM, GRU, DeepAR, and Transformers. Their complexity grows as largermodels are developed, requiring large training sample sizes and computationalresources. So, it is crucial to determine if the complexity brought in by DNN-basedmethods is a necessary price to pay for a gain in performance. We need a generalcomparison covering all families of methods to allow us to answer this questionwithin the specific application of the research.The novel strategy aims to model the relationship between ESG scores, returns andrisk measures, addressing the following:1. Multi-horizon forecasting , i.e. the prediction at multiple future time steps2. Use various data sources, i.e. available information about the future, exogenoustime series, and static metadata, without prior knowledge of how they interact.3. Interpretability, i.e. identify (i) globally-important variables for the predictionproblem, (ii) persistent temporal patterns, (iii) significant events.4. Implementation of the overall strategy in Python and R language to facilitatedissemination of the results.

The candidate is expected to have a good background in Statistics, including a goodknowledge of data management, data analysis, inference, statistical modelling, andstatistical learning. Good knowledge of programming, algorithms and data structures,including a high-level programming language like Python and/or R, is also necessary.Knowledge of machine learning, neural network modelling, and optimisation will be aplus. A background in Econometrics with good programming and computational skillswill also be considered.

The Department of Economics and Statistics research team has a tradition ofresearch in neural networks and deep learning, time series analysis, and financialeconometrics models (parametric and nonparametric, univariate and multivariate) forrisk analysis and portfolio management. The research team has published ininternational journals, including the International Journal of Forecasting, InternationalJournal of Approximate Reasoning, Annals of Statistics, JASA, Econometrics and Statistics, Journal of Machine Learning Research, Journal of Nonparametric Statistics, Statistical Analysis and Data Mining, Soft Computing