Sökning: "double machine learning"

Visar resultat 1 - 5 av 35 uppsatser innehållade orden double machine learning.

  1. 1. Double Machine Learning for Insurance Price Optimization

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Jakob Kristiansson; [2023]
    Nyckelord :DML; Double Machine Learning; Price Optimization; Insurance Pricing; DML; Dubbel Maskininlärning; Prisoptimering; Försäkringsprissättning;

    Sammanfattning : This thesis examines how recent advances in debaised machine learning can be used for estimating price elasticities of demand within the automotive insurance field. Traditional methods such as generalized linear model (GLM) to estimate demand has no way of ensuring there are no biases in the underlying data selection, especially when the confounding variables are many. LÄS MER

  3. 2. Machine Learning for Pulse Shape Analysis of Heavy Ions

    Magister-uppsats, Uppsala universitet/Tillämpad kärnfysik

    Författare :Steven Hendrik Bijl; [2023]
    Nyckelord :Heavy Ions; Machine Learning;

    Sammanfattning : Most of the Generation IV nuclear reactors designs are intended to operate with a fast neutron spectrum. This necessitates further investigation into nuclear fuel behaviour because fast neutrons yield a higher neutron multiplicity with fission fragments, significantly impacting the criticality assessment of these reactors. LÄS MER

  4. 3. The Impact of Parental Education on the Early Detection of Autism Spectrum Disorder in Children.

    Master-uppsats, Lunds universitet/Nationalekonomiska institutionen

    Författare :Farahim Suleymanli; [2023]
    Nyckelord :ASD; DML; PLR; IRM; early detection; parental education; causal inference; Business and Economics;

    Sammanfattning : Utilizing the Double Machine Learning (DML) framework with both Partially Linear Regression (PLR) and Interactive Regression Models (IRM), this study examined the crucial role of parental education in the early detection of Autism Spectrum Disorder (ASD). Analysis was conducted on comprehensive data from the National Survey of Children's Health spanning the years 2017 to 2021. LÄS MER

  5. 4. A Causal Analysis of Cat Bond Markets

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

    Författare :Tim Matheis; [2023]
    Nyckelord :Cat bonds; Insurance-linked securities; Causal machine learning; Random forests;

    Sammanfattning : This work is a contribution to the causal analysis of the catastrophe bond market, which has generated high excess returns over the last two decades. Since these excess returns remain partially unexplainable and the interest in catastrophe bonds is increasing, the causal study of the factors affecting their premiums is of high relevance. LÄS MER

  7. 5. Mobile Traffic Classification and Multi-Cell Base Station Control for Energy-Efficient 5G Networks

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

    Författare :Cai Tianzhang; [2023]
    Nyckelord :;

    Sammanfattning : The global energy consumption of mobile networks is rapidly increasing due to the exponential growth of mobile network traffic. The advent of next-generation cellular technologies such as fifth-generation (5G) and beyond promises higher network throughput and lower latency but also demands higher power consumption for its denser base station (BS) deployment and more energy-intensive processors. LÄS MER