Sökning: "Aktieprognoser"

Hittade 4 uppsatser innehållade ordet Aktieprognoser.

  1. 1. Evaluation of established and new deep learning models for time series equity securities forecasting

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

    Författare :Gustaf Lidfeldt; Isak Hassbring; [2020]
    Nyckelord :;

    Sammanfattning : In this bachelor thesis we investigate the importance of feature selection when making predictions on time series data. We compare how well different deep neural network models perform within equity securities time series prediction, namely the models RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), LSTM with a peephole connection and last but not least GRU (Gated Recurrent Unit). LÄS MER

  2. 2. Trading with Artificial Neural Networks on Large-, Mid- and Small-Cap Stocks : Exploring if Market Cap has an effect on portfolio performance when trading with Artificial Neural Networks trained on historical stock data

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC); KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Patrik Forslind; Lucia Edwards; [2017]
    Nyckelord :;

    Sammanfattning : n this report one-day ahead stock prediction using artificial neural networks (ANN) is studied on stocks belonging to different market caps. Hennes & Mauritz, EnQuest PLC and Rottneros have been selected, representing large-, mid- and small-cap companies. LÄS MER

  3. 3. Examining how unforeseen events affect accuracy and recovery of a non-linear autoregressive neural network in stock market prognoses

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC); KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Nick Nyman; Michel Postigo Smura; [2016]
    Nyckelord :Neural networks; Stock prognosis; Stock analysis; Neuronnät; Neurala nätverk; Aktieprognoser; Aktieanalys;

    Sammanfattning : This report studies how a non-linear autoregressive neural network algorithm for stock market value prognoses is affected by unforeseen events. The study attempts to find out the recovery period for said algorithms after an event, and whether the magnitude of the event affects the recovery period. LÄS MER

  4. 4. Finansiell psykologi : En empirisk studie av olika faktorers påverkan inom finansbranschen

    Kandidat-uppsats, Södertörns högskola/Institutionen för samhällsvetenskaper; Södertörns högskola/Institutionen för samhällsvetenskaper

    Författare :Malin Gustafsson; Johanna Stålberg; [2014]
    Nyckelord :Behavioural Finance; Overconfidence; Herding; Better-than-average; Mood; Finansiell Psykologi; Övertro; Flockbeteende; Sinnesstämning;

    Sammanfattning : Investors have been shown to be driven by emotional and psychological factors. This contradicts classical financial theories, for example the Efficient Market hypothesis which states that all investors act rationally. LÄS MER