Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms
Currency Derivatives are very important financial instruments for speculation, hedging and arbitrage opportunities, and among them cross-country futures are one of the important types with a huge research gap. Studying them becomes very imperative. This paper studies the volatility of INR based cros...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dunarea de Jos University of Galati
2024-12-01
|
| Series: | Annals of Dunarea de Jos University. Fascicle I : Economics and Applied Informatics |
| Subjects: | |
| Online Access: | http://eia.feaa.ugal.ro/images/eia/2024_3/Shreevastava_et_al.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846094982930235392 |
|---|---|
| author | Aman Shreevastava Bharat Kumar Meher Virgil Popescu Ramona Birau Mritunjay Mahato |
| author_facet | Aman Shreevastava Bharat Kumar Meher Virgil Popescu Ramona Birau Mritunjay Mahato |
| author_sort | Aman Shreevastava |
| collection | DOAJ |
| description | Currency Derivatives are very important financial instruments for speculation, hedging and arbitrage opportunities, and among them cross-country futures are one of the important types with a huge research gap. Studying them becomes very imperative. This paper studies the volatility of INR based cross country futures (USD, JPY and EUR) and performs forecasting using ML Algorithm and utilizes LSTM for prediction. The study proves to be a first of its kind study involving cross-country futures and is a beacon of hope for all future research on similar subjects. The study will also be helpful to investors and foreign exchange managers along with monetary and fiscal policymakers. The study consists of total of 674 data points of near-month expiry futures expiring on 29th October, 2024. The span of data was 1 year for JPY and EUR and nearly 11 months for USD. The data were downloaded from NSE website. The USD-INR futures were nearly stable and EUR-INR futures were most volatile. The JPY-INR futures had highest rise in price trends. Prediction of USD/INR future outperformed other two with least error. However, LSTM model that was trained, relatively underperformed in case of JPY-INR. |
| format | Article |
| id | doaj-art-ffb5d08af4fa4a7195ad5d9b147259a5 |
| institution | Kabale University |
| issn | 1584-0409 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Dunarea de Jos University of Galati |
| record_format | Article |
| series | Annals of Dunarea de Jos University. Fascicle I : Economics and Applied Informatics |
| spelling | doaj-art-ffb5d08af4fa4a7195ad5d9b147259a52025-01-02T11:53:39ZengDunarea de Jos University of GalatiAnnals of Dunarea de Jos University. Fascicle I : Economics and Applied Informatics1584-04092024-12-01303146155doi.org/10.35219/eai15840409439Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning AlgorithmsAman Shreevastava0Bharat Kumar Meher1Virgil Popescu2Ramona Birau3Mritunjay Mahato4 PG Department of Commerce and Management, Purnea University, Purnia, Bihar, IndiaDepartment of Commerce, D. S. College, Katihar, Bihar, IndiaFaculty of Economics and Business Administration, University of Craiova, Romania"Eugeniu Carada" Doctoral School of Economic Sciences, University of Craiova, RomaniaSchool of Commerce and Management, Srinath University, IndiaCurrency Derivatives are very important financial instruments for speculation, hedging and arbitrage opportunities, and among them cross-country futures are one of the important types with a huge research gap. Studying them becomes very imperative. This paper studies the volatility of INR based cross country futures (USD, JPY and EUR) and performs forecasting using ML Algorithm and utilizes LSTM for prediction. The study proves to be a first of its kind study involving cross-country futures and is a beacon of hope for all future research on similar subjects. The study will also be helpful to investors and foreign exchange managers along with monetary and fiscal policymakers. The study consists of total of 674 data points of near-month expiry futures expiring on 29th October, 2024. The span of data was 1 year for JPY and EUR and nearly 11 months for USD. The data were downloaded from NSE website. The USD-INR futures were nearly stable and EUR-INR futures were most volatile. The JPY-INR futures had highest rise in price trends. Prediction of USD/INR future outperformed other two with least error. However, LSTM model that was trained, relatively underperformed in case of JPY-INR.http://eia.feaa.ugal.ro/images/eia/2024_3/Shreevastava_et_al.pdfcross-currency derivativesfuturesmachine learning (ml) algorithmslstmvolatilityneural networkforecasting |
| spellingShingle | Aman Shreevastava Bharat Kumar Meher Virgil Popescu Ramona Birau Mritunjay Mahato Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms Annals of Dunarea de Jos University. Fascicle I : Economics and Applied Informatics cross-currency derivatives futures machine learning (ml) algorithms lstm volatility neural network forecasting |
| title | Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms |
| title_full | Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms |
| title_fullStr | Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms |
| title_full_unstemmed | Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms |
| title_short | Assessing Volatility Behaviors of Cross-Currency Derivatives in India's Exchange Markets Using Machine Learning Algorithms |
| title_sort | assessing volatility behaviors of cross currency derivatives in india s exchange markets using machine learning algorithms |
| topic | cross-currency derivatives futures machine learning (ml) algorithms lstm volatility neural network forecasting |
| url | http://eia.feaa.ugal.ro/images/eia/2024_3/Shreevastava_et_al.pdf |
| work_keys_str_mv | AT amanshreevastava assessingvolatilitybehaviorsofcrosscurrencyderivativesinindiasexchangemarketsusingmachinelearningalgorithms AT bharatkumarmeher assessingvolatilitybehaviorsofcrosscurrencyderivativesinindiasexchangemarketsusingmachinelearningalgorithms AT virgilpopescu assessingvolatilitybehaviorsofcrosscurrencyderivativesinindiasexchangemarketsusingmachinelearningalgorithms AT ramonabirau assessingvolatilitybehaviorsofcrosscurrencyderivativesinindiasexchangemarketsusingmachinelearningalgorithms AT mritunjaymahato assessingvolatilitybehaviorsofcrosscurrencyderivativesinindiasexchangemarketsusingmachinelearningalgorithms |