| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Mangeloja, Esa", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Nyholm, Sebastian", "language": null, "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2024-05-06T11:02:48Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2024-05-06T11:02:48Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2024", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/94711", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "This study presents a quantitative comparison of three different option pricing models. The emphasis is on the quite recent artificial neural network model, which is compared to the Monte Carlo simulation and the Black-Scholes-Merton pricing model. The financial markets' complexity demands increasingly sophisticated models, and recent advances in computing power have facilitated the development of intricate option pricing models.\r\nEspecially the sub-model derived from artificial neural networks, the multilayer perceptron has been used in pricing European call options. Existing literature demonstrates the multilayer perceptron's superiority in pricing accuracy compared to the Black-Scholes-Merton model. However, successful implementation necessitates specific model inputs, defined network architecture, and a substantial amount of data.\r\nThe results of this study underscore the better predictive accuracy of the artificial neural networks when compared to the stochastic models, as it is more accurate in predicting the option prices when using the complete testing dataset. Notably, the artificial neural network exhibits exceptional performance when pricing out-of-the-money options, with diminishing discrepancies to the stochastic models observed with in-the-money options, to the point of the network\u2019s results being comparable to the results of the stochastic models. The two stochastic models used in this thesis expectedly perform extremely similarly.\r\nThe optimal network architecture identified diverges notably from those architectures used in prior literature, featuring significantly greater numbers of hidden layers and neurons per layer. However, despite the large network size this does not cause overfitting problems, and this is somewhat attributable to the large reliable dataset. The time period used, along with the chronological data partitioning method, caused problems, ultimately leading to the decision to drop the interest rate variable from the network model altogether.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "T\u00e4m\u00e4 tutkimus vertailee kolmea erilaista optioiden hinnoittelumallia kvantita-tiivisesti. Painopiste on melko uuden keinotekoisen neuroverkkomallin k\u00e4y-t\u00f6ss\u00e4, jota vertaillaan Monte Carlo simulaatioon sek\u00e4 Black-Scholes-Merton hinnoittelumalliin. Rahoitusmarkkinoiden monimutkaisuus sek\u00e4 sen data-massat vaativat monimutkaisempien mallien k\u00e4ytt\u00f6\u00e4 kuin koskaan aikaisem-min, ja viimeaikaiset edistysaskeleet laskentatehossa ovat mahdollistaneet hienovaraisten hinnoittelumallien kehityksen. \r\nErityisesti keinotekoisten neuroverkkojen alamallia monikerroksista perseptroniverkkoa on k\u00e4ytetty eurooppalaisten osto-optioiden hinnoittelussa. Kirjallisuus todistaa monikerroksisten perseptroniverkkojen olevan tarkempia Black-Scholes-Merton malliin verrattuna, vaikkakin tietynlaiset sy\u00f6tteet, verkkoarkkitehtuuri sek\u00e4 suuri datasetti ovat v\u00e4ltt\u00e4m\u00e4tt\u00f6mi\u00e4 t\u00e4m\u00e4n tarkkuuden saavuttamiseksi. \r\nT\u00e4m\u00e4n tutkimuksen tulokset korostavat keinotekoisten neuroverkkojen tarkempaa hinnoittelua verrattuna stokastisiin malleihin, sill\u00e4 ne ovat tarkempia optiohinnoittelussa, kun k\u00e4ytet\u00e4\u00e4n vertailussa koko datasetti\u00e4. Keinotekoinen neuroverkko osoittaa poikkeuksellista suorituskyky\u00e4 miinusoptioilla (out-of-the-money), ja erot stokastisiin malleihin pienenev\u00e4t siirrytt\u00e4ess\u00e4 plusoptioihin (in-the-money), joka johtaa mallien samantasoiseen suorituskykyyn plusoptioilla. Tutkimuksessa k\u00e4ytett\u00e4v\u00e4t stokastiset mallit suoriutuivat odotetusti eritt\u00e4in samankaltaisesti.\r\nTuloksissa tunnistettu optimaalinen neuroverkkorakenne poikkeaa huomattavasti aiemmassa kirjallisuudessa k\u00e4ytetyist\u00e4 rakenteista, sill\u00e4 siin\u00e4 on merkitt\u00e4v\u00e4sti enemm\u00e4n piilokerroksia sek\u00e4 neuroneita per kerros. Vastoin odotuksia suuri koko ei kuitenkaan aiheuta ylisovittamisongelmia, mik\u00e4 johtuu osittain suuresta ja luotettavasta datasetist\u00e4. K\u00e4ytetty aikaperiodi kronologisen jaottelun kanssa aiheuttaa ongelmia ja t\u00e4m\u00e4 johtaa lopulta korkotaso muuttujan poistamiseen neuroverkkomallista kokonaan.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by jyx lomake-julkaisija (jyx-julkaisija.group@korppi.jyu.fi) on 2024-05-06T11:02:48Z\r\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2024-05-06T11:02:48Z (GMT). No. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "73", "language": null, "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "eng", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "CC BY 4.0", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.title", "value": "Quantitative comparison of option pricing models: neural networks vs. stochastic models", "language": null, "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202405063478", "language": null, "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master's thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Jyv\u00e4skyl\u00e4 University School of Business and Economics", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Jyv\u00e4skyl\u00e4n yliopiston kauppakorkeakoulu", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Economics", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Taloustiede", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.copyright", "value": "\u00a9 The Author(s)", "language": null, "element": "rights", "qualifier": "copyright", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://creativecommons.org/licenses/by/4.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}]
|