dc.contributor.advisor |
Nardon, Martina |
it_IT |
dc.contributor.author |
Ropele, Andrea <1994> |
it_IT |
dc.date.accessioned |
2018-06-20 |
it_IT |
dc.date.accessioned |
2018-12-03T06:20:45Z |
|
dc.date.issued |
2018-07-02 |
it_IT |
dc.identifier.uri |
http://hdl.handle.net/10579/13238 |
|
dc.description.abstract |
This thesis wants to put together the area of computer science and statistics. For the IT side, the mechanisms of the blockchain technology and classical concept of computer science necessary for understanding it will be outlined. On the other hand, the quantitative part will present the state of the art of machine learning algorithms. The work will end with an empirical chapter where machine learning methods will be compared to classical statistical models. The comparison metric will be the forecasting error of the conditional mean and the conditional variance of timeseries belonging to the cryptocurrency world. |
it_IT |
dc.language.iso |
en |
it_IT |
dc.publisher |
Università Ca' Foscari Venezia |
it_IT |
dc.rights |
© Andrea Ropele, 2018 |
it_IT |
dc.title |
The Blockchain technology and a comparison between classical statistical models
and machine learning methods for time series analysis |
it_IT |
dc.title.alternative |
The Blockchain technology and a comparison between classical statistical models and machine learning methods for time series analysis |
it_IT |
dc.type |
Master's Degree Thesis |
it_IT |
dc.degree.name |
Economia e finanza |
it_IT |
dc.degree.level |
Laurea magistrale |
it_IT |
dc.degree.grantor |
Dipartimento di Economia |
it_IT |
dc.description.academicyear |
2017/2018, sessione estiva |
it_IT |
dc.rights.accessrights |
closedAccess |
it_IT |
dc.thesis.matricno |
861522 |
it_IT |
dc.subject.miur |
SECS-P/05 ECONOMETRIA |
it_IT |
dc.description.note |
This thesis wants to put together the area of computer science and statistics. For the IT side, the mechanisms of the blockchain technology and classical concept of computer science necessary for understanding it will be outlined. On the other hand, the quantitative part will present the most popular machine learning algorithms, along with some practical examples. The work will end with an empirical chapter where neural networks will be compared to classical statistical models. The comparison metric will be the forecasting performance of the conditional variance of financial timeseries belonging to the cryptocurrency world. |
it_IT |
dc.degree.discipline |
|
it_IT |
dc.contributor.co-advisor |
|
it_IT |
dc.date.embargoend |
10000-01-01 |
|
dc.provenance.upload |
Andrea Ropele (861522@stud.unive.it), 2018-06-20 |
it_IT |
dc.provenance.plagiarycheck |
Martina Nardon (mnardon@unive.it), 2018-07-02 |
it_IT |