Now showing items 1-20 of 30

    • A comparative study of demand forecasting models for an online retailer business 

      Lorenzo Villagrasa, Raul (Universitat Politècnica de Catalunya, 2021-06-30)
      Master thesis
      Restricted access - author's decision
    • A deep learning approach to portfolio optimization 

      Cartanyà Caro, Pau (Universitat Politècnica de Catalunya, 2022-02)
      Bachelor thesis
      Open Access
      Covenantee:   Hong Kong University of Science and Technology
      Des del desenvolupament de la teoria moderna de carteres de Markowitz l'any 1952, s'han dut a terme numerosos avenços per a millorar-ne les tècniques originals, fins al punt que la recerca actual en aquest àmbit es centra ...
    • A machine learning approach to stock screening with fundamental analysis 

      Alvarez Vecino, Pol (Universitat Politècnica de Catalunya, 2019-04-15)
      Master thesis
      Open Access
      We present HPC.FASSR, a High-Performance Computation Fundamental Analysis Stock Screener and Ranker to compare many ML models and the criteria of famous Benjamin Graham for stock investing using fundamental data. FASSR is ...
    • A machine learning approach to the optimal estimation of portfolio weights 

      Cusiné Jiménez, Irene (Universitat Politècnica de Catalunya, 2022-07)
      Bachelor thesis
      Open Access
      Covenantee:   École polytechnique fédérale de Lausanne
      The purpose of this thesis is to review and expand the main result in the paper by Daniel Kinn, "Reducing Estimation Risk in Mean-Variance Portfolios with Machine Learning (preprint arXiv:1804.01764 (2018)). This result ...
    • A mathematical proof of the soundness of the Fibonacci retracement rule in technical analysis of asset prices 

      Pujadas Ramalhinho, Vera (Universitat Politècnica de Catalunya, 2021-01)
      Bachelor thesis
      Open Access
      This project covers the idea of the Fibonacci retracement rule and its mathematical proof. Firstly, a thorough analysis of stochastic processes, in particular, diffusion processes such as the Brownian motion, the CEV model ...
    • A Review of Regression Trees Algorithms in C++ and their application 

      Hernández Escavy, Jesús (Universitat Politècnica de Catalunya, 2019-06)
      Bachelor thesis
      Open Access
      En aquesta tesis s'ha desenvolupat un software de generació d'arbres de decisió que fa completament autoexplicatius els arbres generats ja que, a més de la construcció del mateix, s'ha inclòs un conversor de regles lògiques ...
    • A study of Deep Learning techniques for sequence-based problems 

      Quintana Valenzuela, Diego (Universitat Politècnica de Catalunya, 2021-10)
      Master thesis
      Restricted access - author's decision
      Transformer Networks are a new type of Deep Learning architecture first introduced in 2017. By only applying attention mechanisms, the transformer network can model relations between text sequences that outperformed other ...
    • Adding support for multi-analytes medical drugs in a software called Tucuxi 

      Climent I Gutiérrez, Alex (Universitat Politècnica de Catalunya, 2022-04-26)
      Bachelor thesis
      Restricted access - confidentiality agreement
    • Analysis on distance metrics approaches in graphs and their applications 

      Cebollero Ruiz, Laura (Universitat Politècnica de Catalunya, 2019-07-05)
      Master thesis
      Restricted access - confidentiality agreement
    • Conic portfolio theory 

      Ferrer Fernàndez, Sergi (Universitat Politècnica de Catalunya, 2016-07)
      Master thesis
      Open Access
      Conic financial theory is based on the existence of a two price economy (bid and ask prices) for market valuation and risk measures. We study the portfolio selection problem within the framework of conic finance. With this ...
    • Deep learning based Recommender System for an online retailer 

      Breve Ramírez, Manuel Alejandro (Universitat Politècnica de Catalunya, 2021-10-29)
      Master thesis
      Restricted access - author's decision
      Since Wide and Deep Learning for Recommender Systems appeared in 2016, multiple architecture models have been created around this idea of jointly train a wide and deep neural networks as this architecture allow the model ...
    • Detecting clusters and their dynamics in the Forex Market 

      Renedo Mirambell, Martí (Universitat Politècnica de Catalunya, 2016-07)
      Bachelor thesis
      Open Access
      This project studies and implements the clustering methods introduced by Fenn et al. to detect correlations in the foreign exchange market. To deal with the potentially non linear nature of currency time series dependance, ...
    • Do Stop-Loss rules stop losses? An analytical framework based on modeling overnight gaps and the Stationary Bootstrap 

      Dorador Chalar, Albert (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2017-06)
      Master thesis
      Open Access
      Aquest treball, que te per titol definitiu "Do Stop-Loss rules stop losses? An analytical framework based on modeling overnight gaps and the Stationary Bootstrap", presenta una analisi amplia i profunda sobre la utilitat ...
    • Exploring linkages between international stock markets using Graphical models for multivariate time series 

      Mohammadi, Gehlavij (Universitat Politècnica de Catalunya, 2014-01)
      Master thesis
      Open Access
      In this thesis we apply graphical statistics models for analyzing causality relations among various international stock markets. We present Graphical models in terms of conditional independence in probability spaces, as ...
    • Feature engineering, dimensionality reduction and interpretability through autoencoders for structured data 

      Bofarull Cabello, Antoni (Universitat Politècnica de Catalunya, 2021-06-30)
      Master thesis
      Open Access
      Machine Learning is the area of Artificial Intelligence where algorithms learn from data. Therefore, making a good selection of features is essential for the models to perform their tasks in the best possible way. We employ ...
    • Forecasting financial time series using multiple Kernel Learning 

      Fábregues de los Santos, Luis (Universitat Politècnica de Catalunya, 2017-07-05)
      Master thesis
      Open Access
      This thesis introduces a forecasting procedure based on Multiple Kernel Learning to predict and measure the influence of several economic variables in the process of predicting the equity premium of the S&P 500 Index. ...
    • High-precision computation of uniform asymptotic expansions for special functions 

      Navas Palencia, Guillermo (Universitat Politècnica de Catalunya, 2019-07-22)
      Doctoral thesis
      Open Access
      In this dissertation, we investigate new methods to obtain uniform asymptotic expansions for the numerical evaluation of special functions to high-precision. We shall first present the theoretical and computational fundamental ...
    • Multiple classifier performance 

      Duarte López, Ariel (Universitat Politècnica de Catalunya, 2015-10)
      Master thesis
      Open Access
    • Multivariate dynamic Kernels for financial time series forecasting 

      Peña-Grass, Mauricio (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2015-06)
      Master thesis
      Restricted access - author's decision
      This thesis proposes a novel forecasting method that elaborates on the capability of integrating information measured at different frequencies and at irregular time intervals in financial markets. A data compression process ...
    • Neural ordinary differential equations: analysis and implementation 

      Romaní Rodés, Marcel (Universitat Politècnica de Catalunya, 2022-06-28)
      Master thesis
      Restricted access - author's decision
      Neural Ordinary Differential Equations (NODE) have emerged as a novel approach to deep learning, where instead of specifying a discrete sequence of hidden layers, it parameterizes the derivative of the hidden state using ...