Eghbal Rahimikia_
Assistant Professor in Financial Technology, Alliance Manchester Business School (AMBS)
I obtained my undergraduate degree in Economics from the University of Tehran (first-class honours), my master's degree in Industrial Engineering from the Iran University of Science and Technology (distinction) and my PhD degree in Finance from the Alliance Manchester Business School (AMBS), the University of Manchester. I am currently an Assistant Professor (Lecturer) in Financial Technology (FinTech) at the Alliance Manchester Business School, working on the theory and application of machine learning (ML) and natural language processing (NLP) in Finance. My current project focuses on developing the first comprehensive financial NLP repository, FinText, in collaboration with researchers and industry partners. This repository covers a variety of NLP models (from Word2Vec to GPT) and benchmarks, incorporating different big financial textual datasets.
NEWS:
University of Manchester, UK
Alliance Manchester Business School (AMBS)
2018 - 2023 (March)
Ph.D. in Finance.
Supervisor: Ser-Huang Poon.
Examination Committee: Stephen Roberts (University of Oxford), Stuart Hyde (University of Manchester).
GPA: Distinction.
Iran University of Science and Technology, Iran
2012 - 2014
M.Sc. in Industrial Engineering.
Major: Socio-Economical Systems Engineering.
Thesis: Bankruptcy prediction of Iranian companies based on hybrid intelligent systems.
GPA: 18.33/20, Thesis grade: 20/20 (distinction).
University of Tehran, Iran
2009 - 2012
B.A. in Economics.
GPA: 18.42/20 (first-class honours).
Assistant Professor in Financial Technology (FinTech)
University of Manchester, UK
Agusut 2023 - Cur.
Consultant
Hull Tactical Asset Allocation, US
Agusut 2023 - Cur.
Lecturer in Finance
University of Manchester, UK
Sep 2021 - Agusut 2023
Research Assistant Intern
University of Oxford, UK
Jan 2021 - Apr 2021
Graduate Teaching Assistant
University of Manchester, UK
Sep 2019 - Sep 2021
CEO Consultant
Omid Investment Management Group Co, Iran
Jul 2017 - Dec 2017
Project manager/Software developer
Iranian National Tax Administration, Iran
Jul 2014 - Jul 2017
This paper tests if the limit order book (LOB) and news stories from 27 July 2007 to 27 January 2022 can help forecast realised volatility (RV) for stocks.
Keywords:
https://dx.doi.org/10.2139/ssrn.3684040his paper compares machine learning (ML) and HAR class of models for forecasting realised volatility using 147 input variables extracted from limit order book (LOB), and stock-specific news stories for the period from 27 July 2007 to 27 January 2022.
Keywords:
http://dx.doi.org/10.2139/ssrn.3707796This study develops FinText, a financial word embedding compiled from 15 years of business news archives. The results show that FinText produces substantially more accurate results than general word embeddings based on the gold-standard financial benchmark we introduced.
Keywords:
http://dx.doi.org/10.2139/ssrn.3895272Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
Rahimikia, Eghbal, Stefan Zohren, and Ser-Huang Poon
Available at SSRN 3895272 (2021). 2021
Machine Learning for Realised Volatility Forecasting
Rahimikia, Eghbal and Ser-Huang Poon
Available at SSRN 3707796 (2020). 2020
Alternative Data for Realised Volatility Forecasting: Limit Order Book and News Stories
Rahimikia, Eghbal and Ser-Huang Poon
Available at SSRN 3684040 (2020). 2020
Detecting corporate tax evasion using a hybrid intelligent system: A case study of Iran
Rahimikia, Eghbal, Shapour Mohammadi, Teymur Rahmani, and Mehdi Ghazanfari
International Journal of Accounting Information Systems 25 (2017) pp. 1–17. Elsevier, 2017
Get in touch_