Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Le rapport suivant a été écrit dans le cadre de mon stage dans l'entreprise « Behave! ». Son principal objectif est d’identifier et de défendre le modèle de Machine Learning le plus pertinent dans la cadre de prévisions portant sur 7 styles d’investissement différents : « Growth », « Momentum », « Quality », « Size », « Value », « Volatility » et « Yield ».

Étant donné que ce mémoire est rédigé selon une orientation "rapport d’entreprise", une part importante de ce document est consacrée à la construction de modèles et à l’analyse de résultats.

De nombreuses recherches académiques ont néanmoins dû être effectuées et viendront, aussi souvent que possible, appuyer les conclusions établies au fur et à mesure des chapitres.

Ma tâche au sein de l’entreprise peut être divisée en trois étapes majeures, il en va de même pour la construction de ce rapport.
Premièrement, les facteurs de risque sont définis et systématiquement liés à leurs styles d’investissement. C’est l’occasion d’étudier les techniques utilisées par l’entreprise pour les calculer.

Dans un deuxième temps, ce sont les modèles de Machine Learning qui sont définis et appliqués à un exemple simple en utilisant les logiciels « RStudio » et « Microsoft Azure Cortana Intelligence ». Dans ce mémoire, l’approche se limite aux modèles suivants : « Hidden Markov », « Random Forest », « Support Vector Machine » et « Neural Network ».

Il s’agira enfin d’appliquer ces modèles aux styles d’investissement proposés par l’entreprise afin de pouvoir faire des comparaisons qui serviront ensuite de base à mes recommandations finales.

Machine Learning, factor investing, growth, momentum, quality, size, --- value, volatility, hidden markov, support vector machine, neural --- network, random forest, artificial intelligence, confusion matrix, --- performance, accuracy, investment, ESG criteria --- Sciences économiques & de gestion > Finance --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Modern computer technology has opened up new opportunities for the development of digital signal processing methods. The applications of digital signal processing have expanded significantly and today include audio and speech processing, sonar, radar, and other sensor array processing, spectral density estimation, statistical signal processing, digital image processing, signal processing for telecommunications, control systems, biomedical engineering, and seismology, among others. This Special Issue is aimed at wide coverage of the problems of digital signal processing, from mathematical modeling to the implementation of problem-oriented systems. The basis of digital signal processing is digital filtering. Wavelet analysis implements multiscale signal processing and is used to solve applied problems of de-noising and compression. Processing of visual information, including image and video processing and pattern recognition, is actively used in robotic systems and industrial processes control today. Improving digital signal processing circuits and developing new signal processing systems can improve the technical characteristics of many digital devices. The development of new methods of artificial intelligence, including artificial neural networks and brain-computer interfaces, opens up new prospects for the creation of smart technology. This Special Issue contains the latest technological developments in mathematics and digital signal processing. The stated results are of interest to researchers in the field of applied mathematics and developers of modern digital signal processing systems.

digital filter --- finite field algebra --- conversion device --- module --- memory device --- residue --- feedback regulation --- digital signal analysis --- control efficacy --- residue number system --- redundant residue number system --- modular division --- fraction --- algorithm --- mathematical models of digital signal processing --- digital filtering --- maximum correntropy --- impulsive noise --- sparse channel estimation --- discrete wavelet transform --- medical imaging --- 3D image processing --- quantization noise --- harmonic wavelets --- classification --- kNN-algorithm --- deep neural networks --- machine learning --- Fourier transform --- short-time Fourier transform --- wavelet transform --- spectrogram --- confusion matrix --- ROC curve --- 3D model --- prosthetic design --- orientation --- positioning --- reconstruction --- speech enhancement --- adaptive filter --- microphone array --- sub-band processing --- filter bank --- posture classification --- skeleton detection --- motion capture --- exercise classification --- virtual rehabilitation --- wood defect --- CNN --- ELM --- genetic algorithm --- detection

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Modern computer technology has opened up new opportunities for the development of digital signal processing methods. The applications of digital signal processing have expanded significantly and today include audio and speech processing, sonar, radar, and other sensor array processing, spectral density estimation, statistical signal processing, digital image processing, signal processing for telecommunications, control systems, biomedical engineering, and seismology, among others. This Special Issue is aimed at wide coverage of the problems of digital signal processing, from mathematical modeling to the implementation of problem-oriented systems. The basis of digital signal processing is digital filtering. Wavelet analysis implements multiscale signal processing and is used to solve applied problems of de-noising and compression. Processing of visual information, including image and video processing and pattern recognition, is actively used in robotic systems and industrial processes control today. Improving digital signal processing circuits and developing new signal processing systems can improve the technical characteristics of many digital devices. The development of new methods of artificial intelligence, including artificial neural networks and brain-computer interfaces, opens up new prospects for the creation of smart technology. This Special Issue contains the latest technological developments in mathematics and digital signal processing. The stated results are of interest to researchers in the field of applied mathematics and developers of modern digital signal processing systems.

Information technology industries --- digital filter --- finite field algebra --- conversion device --- module --- memory device --- residue --- feedback regulation --- digital signal analysis --- control efficacy --- residue number system --- redundant residue number system --- modular division --- fraction --- algorithm --- mathematical models of digital signal processing --- digital filtering --- maximum correntropy --- impulsive noise --- sparse channel estimation --- discrete wavelet transform --- medical imaging --- 3D image processing --- quantization noise --- harmonic wavelets --- classification --- kNN-algorithm --- deep neural networks --- machine learning --- Fourier transform --- short-time Fourier transform --- wavelet transform --- spectrogram --- confusion matrix --- ROC curve --- 3D model --- prosthetic design --- orientation --- positioning --- reconstruction --- speech enhancement --- adaptive filter --- microphone array --- sub-band processing --- filter bank --- posture classification --- skeleton detection --- motion capture --- exercise classification --- virtual rehabilitation --- wood defect --- CNN --- ELM --- genetic algorithm --- detection