Sökning: "Marknadsövervakning"

Visar resultat 1 - 5 av 8 uppsatser innehållade ordet Marknadsövervakning.

  1. 1. Market Surveillance Using Empirical Quantile Model and Machine Learning

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Daniel Landberg; [2022]
    Nyckelord :Market surveillance; Outlier detection; Empirical quantiles; Empirical distribution; Isolation forest; Principal Component Analysis; PCA; Finance; Marknadsövervakning; Extremvärdes upptäckt; Empiriska kvantiler; Empirisk distribution; Isolationsskog; Huvudkomponent analys; Finans;

    Sammanfattning : In recent years, financial trading has become more available. This has led to more market participants and more trades taking place each day. The increased activity also implies an increasing number of abusive trades. To detect the abusive trades, market surveillance systems are developed and used. LÄS MER

  3. 2. Federated Learning for Market Surveillance

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

    Författare :Philip Song; [2022]
    Nyckelord :Federated Learning; Machine Learning; Market Surveillance; Anomaly Detection; LSTMAutoencoder; Federated Learning; Maskininlärning; Marknadsövervakning; Anomaliupptäckande; LSTMAutoencoder;

    Sammanfattning : The increasing complexity of trading strategies, when combined with machine learning models, forces market surveillance corporations to develop increasingly sophisticated methods for recognizing potential misuse. One strategy is to employ traders’ weapons against themselves, namely machine learning. LÄS MER

  4. 3. Explainable Deep Learning Methods for Market Surveillance

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

    Författare :Marcus Jonsson Ewerbring; [2021]
    Nyckelord :Deep Learning; Machine Learning; Explainable Deep Learning; XAI; Market Surveillance; Djupinlärning; Maskininlärning; Förklarbar Djupinlärning; XAI; Marknadsövervakning;

    Sammanfattning : Deep learning methods have the ability to accurately predict and interpret what data represents. However, the decision making of a deep learning model is not comprehensible for humans. This is a problem for sectors like market surveillance which needs clarity in the decision making of the used algorithms. LÄS MER

  5. 4. Information Visualization of Participant Behavior in Market Surveillance

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

    Författare :Badai Kesuma; [2021]
    Nyckelord :Information visualization; User experience; Feature selection; Market surveillance;

    Sammanfattning : Financial markets are now undergoing exponential growth in data, as high-frequency trading is widespread. The need for effective market surveillance is, therefore, become more prominent. Domain experts in exchanges, trading participants, and regulators must provide evidence in their market surveillance investigation. LÄS MER

  7. 5. Energy Market Surveillance in the EU and US: A Study of Market Designs, Regulations, and Detection  Algorithms

    Master-uppsats, KTH/Energiteknik

    Författare :Jonas Viktor van Stappen; [2018]
    Nyckelord :;

    Sammanfattning : The need for market surveillance in the context of wholesale energy trading is examined through a study of twenty years of energy market liberalisation, resulting modern market designs in EU and US power and gas markets, and through an exploration of high-profile case studies of energy market abuse. Additionally, an extensive regulatory analysis of core EU (REMIT, MAR, MiFID II) and US (CEA/Dodd-Frank Act, Energy Policy Act, EISA) market regulations is conducted, with the goal of clearly identifying current obligations and prohibitions in their application to wholesale energy market actors. LÄS MER