Predviđanje cena kriptovaluta upotrebom ARIMA i ARIMAKS modela
Ključne reči:
Kriptovalute, ARIMA, ARIMAKS
Apstrakt
Ovaj rad se bavi predviđanjem cena Dodžkoin, Šiba Inu i Idena kriptovaluta u kratkom i srednjem roku upotrebom ARIMA i ARIMAKS modela. Podaci su preuzimani sa različitih javno dostupnih izvora, vremenske serije pretprocesirane kako bi se osigurala stacionarnost, a parametri modela birani pretragom kombinacija parametara i putem auto arima funkcije. Testirani su različiti intervali predviđanja, a modeli evaluirani Akaike informacionim kriterijumom i greškom u apsolutnom procentu. Za kratkoročna predviđanja ARIMA model je imao grešku od oko 3.5%, ARIMAKS od 7 do 19%, dok su se za srednji rok oba modela pokazala kao loša.
Reference
[1] Chohan, Usman W. "A history of Dogecoin." Discussion Series: Notes on the 21st Century (2021).
[2] https://shibatoken.com/ (pristupljeno u maju 2022.)
[3] https://docs.idena.io/docs/wp/summary/ (pristupljeno u maju 2022.)
[4] Azari, Amin. "Bitcoin price prediction: An ARIMA approach." arXiv preprint arXiv:1904.05315 (2019).
[5] Scalzotto, Giovanni. "Social Media Impact on Cryptocurrencies." (2021).
[6] Peter, Ďurka, and Pastoreková Silvia. "ARIMA vs. ARIMAX–which approach is better to analyze and
forecast macroeconomic time series." Proceedings of 30th international conference mathematical methods in economics. Vol. 2. 2012.
[7] Mahan, Margaret & Chorn, Chelley & Georgopoulos, Apostolos. (2015). White Noise Test: detecting autocorrelation and nonstationarities in long time series after ARIMA modeling. 10.25080/Majora-7b98e3ed-00f.
[8] https://finance.yahoo.com/ (pristupljeno u maju 2022.)
[9] https://www.coingecko.com/ (pristupljeno u maju 2022.)
[10] https://trends.google.com/ (pristupljeno u maju 2022.)
[2] https://shibatoken.com/ (pristupljeno u maju 2022.)
[3] https://docs.idena.io/docs/wp/summary/ (pristupljeno u maju 2022.)
[4] Azari, Amin. "Bitcoin price prediction: An ARIMA approach." arXiv preprint arXiv:1904.05315 (2019).
[5] Scalzotto, Giovanni. "Social Media Impact on Cryptocurrencies." (2021).
[6] Peter, Ďurka, and Pastoreková Silvia. "ARIMA vs. ARIMAX–which approach is better to analyze and
forecast macroeconomic time series." Proceedings of 30th international conference mathematical methods in economics. Vol. 2. 2012.
[7] Mahan, Margaret & Chorn, Chelley & Georgopoulos, Apostolos. (2015). White Noise Test: detecting autocorrelation and nonstationarities in long time series after ARIMA modeling. 10.25080/Majora-7b98e3ed-00f.
[8] https://finance.yahoo.com/ (pristupljeno u maju 2022.)
[9] https://www.coingecko.com/ (pristupljeno u maju 2022.)
[10] https://trends.google.com/ (pristupljeno u maju 2022.)
Objavljeno
2022-09-07
Sekcija
Elektrotehničko i računarsko inženjerstvo
