In the field of mortality, the Lee–Carter based approach can be considered the milestone to forecast mortality rates among stochastic models. We could define a “Lee–Carter model family” that embraces all developments of this model, including its first formulation (1992) that remains the benchmark for comparing the performance of future models. In the Lee–Carter model, the ${\kappa }_t$ parameter, describing the mortality trend over time, plays an important role about the future mortality behavior. The traditional ARIMA process usually used to model ${\kappa }_t$ shows evident limitations to describe the future mortality shape. Concerning forecasting phase, academics should approach a more plausible way in order to think a nonlinear shape of the projected mortality rates. Therefore, we propose an alternative approach the ARIMA processes based on a deep learning technique. More precisely, in order to catch the pattern of ${\kappa }_t$ series over time more accurately, we apply a Recurrent Neural Network with a Long Short-Term Memory architecture and integrate the Lee–Carter model to improve its predictive capacity. The proposed approach provides significant performance in terms of predictive accuracy and also allow for avoiding the time-chunks’ a priori selection. Indeed, it is a common practice among academics to delete the time in which the noise is overflowing or the data quality is insufficient. The strength of the Long Short-Term Memory network lies in its ability to treat this noise and adequately reproduce it into the forecasted trend, due to its own architecture enabling to take into account significant long-term patterns.

Corporate social responsibility (CSR) is found to impact firms' performance, for instance, enhancing reputation, increasing innovation capabilities, customer loyalty, and customer satisfaction help improve financial performance. However, the literature provides limited evidence of the relationship between CSR indicators, such as the ESG score, and the firm's profitability, which is often measured by the earnings before interest and taxes (EBIT). We investigate this issue by analyzing a sample of about 400 companies constituting the EuroStoxx‐600 index, from 2011 to 2020, using different machine learning models. The novelty of our contribution lies in assessing whether the ESG score has a significant influence on the firms' profitability. Specifically, we investigate the relationship between ESG score and EBIT using machine learning interpretability toolboxes such as partial dependence plots and individual conditional expectation. Tools which help to measure the functional relationship between the predicted response and one or more features, while the Shapley value allows to examine the contribution of the feature to the prediction. Our findings show that the model can reach high levels of accuracy in detecting EBIT and that the ESG score is a promising predictor, compared to other traditional accounting variables.

Estimation of future mortality rates still plays a central role among life insurers in pricing their products and managing longevity risk. In the literature on mortality modeling, a wide number of stochastic models have been proposed, most of them forecasting future mortality rates by extrapolating one or more latent factors. The abundance of proposed models shows that forecasting future mortality from historical trends is non-trivial. Following the idea proposed in Deprez et al. (2017), we use machine learning algorithms, able to catch patterns that are not commonly identifiable, to calibrate a parameter (the machine learning estimator), improving the goodness of fit of standard stochastic mortality models. The machine learning estimator is then forecasted according to the Lee-Carter framework, allowing one to obtain a higher forecasting quality of the standard stochastic models. Out-of sample forecasts are provided to verify the model accuracy.

This paper follows the recent literature on real estate price prediction and proposes to take advantage of machine learning techniques to better explain which variables are more important in describing the real estate market evolution. We apply the random forest algorithm on London real estate data and analyze the local variables that influence the interaction between housing demand, supply and price. The variables choice is based on an urban point of view, where the main force driving the market is the interaction between local factors like population growth, net migration, new buildings and net supply.