Sökning: "Benjamin Von Essen"

Hittade 3 uppsatser innehållade orden Benjamin Von Essen.

  1. 1. Deep learning, LSTM and Representation Learning in Empirical Asset Pricing

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Benjamin von Essen; [2022]
    Nyckelord :LSTM; empirical asset pricing; deep learning; representation learning; neural networks; LSTM; empirisk tillgångsvärdering; djupinlärning; representationsinlärning; neurala nätverk;

    Sammanfattning : In recent years, machine learning models have gained traction in the field of empirical asset pricing for their risk premium prediction performance. In this thesis, we build upon the work of [1] by first evaluating models similar to their best performing model in a similar fashion, by using the same dataset and measures, and then expanding upon that. LÄS MER

  3. 2. An Empirical Study of Autoencoder Asset Pricing Models and the Impact of Arbitrage Constraints

    D-uppsats, Handelshögskolan i Stockholm/Institutionen för finansiell ekonomi

    Författare :Benjamin von Essen; Haohang Wu; [2021]
    Nyckelord :Empirical asset pricing; Conditional asset pricing model; Machine learning; Arbitrage; Multi-factor model;

    Sammanfattning : Following Gu et al. (2021), we implement a state-of-the-art machine learning asset pricing model, the conditional autoencoder, to capture the time-varying interactions between observable stock characteristics and factor loadings, while simultaneously extracting latent factors from stock returns. LÄS MER

  4. 3. Classifying True and Fake Telecommunication Signals With Deep Learning

    M1-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Axel Myrberger; Benjamin Von Essen; [2020]
    Nyckelord :Deep learning; frequency response; multipathchannel models; WINNER II; hyperparameter search; binaryclassification; feedforward network; neural network;

    Sammanfattning : This project aimed to classified artificiality gener-ated,fake, and authentic,true, telecommunication signals, basedupon their frequency response, using methods from deep learn-ing. Another goal was to accomplish this with the least amountof dimension of data possible. LÄS MER