Style and performance of international socially responsible funds in Europe

This paper analyses the performance and investment styles of internationally oriented Socially Responsible Investment (SRI)funds, domiciled in eight European markets, in comparison with characteristics-matched conventional funds. To the best of our knowledge, this is the first multi-country study, focused on international SRI funds (investing in Global and in European equities), to combine the matched-pairs approach with the use of robust conditional multi-factor performance evaluation models, which allow for both time-varying alphas and betas and also control for home biases and spurious regression biases.In general, the results show that differences in the performance of international SRI funds and their conventional peers are not statistically significant. Regarding investment styles, SRI and conventional funds exhibit similar factor exposures in most cases. In addition,conventional benchmarks present a higher explaining power of SRI fund returns than SRI benchmarks. Our results also show significant differences in the investment styles of SRI funds according to whether they use “best-in-class” screening strategies or not. When compared to SRI funds that employ simple negative and/or positive screens, SRI “best-in-class” funds present significantly lower exposures to small caps and momentum strategies and significantly higher exposures to local stocks.

Artificial neural networks for automatic modelling of the pectus excavatum corrective prosthesis

Pectus excavatum is the most common deformity of the thorax and usually comprises Computed Tomography (CT) examination for pre-operative diagnosis. Aiming at the elimination of the high amounts of CT radiation exposure, this work presents a new methodology for the replacement of CT by a laser scanner (radiation-free) in the treatment of pectus excavatum using personally modeled prosthesis. The complete elimination of CT involves the determination of ribs external outline, at the maximum sternum depression point for prosthesis placement, based on chest wall skin surface information, acquired by a laser scanner. The developed solution resorts to artificial neural networks trained with data vectors from 165 patients. Scaled Conjugate Gradient, Levenberg-Marquardt, Resilient Back propagation and One Step Secant gradient learning algorithms were used. The training procedure was performed using the soft tissue thicknesses, determined using image processing techniques that automatically segment the skin and rib cage. The developed solution was then used to determine the ribs outline in data from 20 patient scanners. Tests revealed that ribs position can be estimated with an average error of about 6.82±5.7 mm for the left and right side of the patient. Such an error range is well below current prosthesis manual modeling (11.7±4.01 mm) even without CT imagiology, indicating a considerable step forward towards CT replacement by a 3D scanner for prosthesis personalization.