Sohom Ghosh
Sr. Data Scientist at Fidelity | Researcher at Jadavpur University
Namaste (নমস্কার) 🙏, I am Sohom. I like developing innovative solutions for solving real life challenges. Over the last 8+ years, I have been toiling to improve digital experience & financial well-being of millions of users across different industries like Internet, Financial Services and so on. Presently, I am working as a Senior Data Scientist for the Artificial Intelligence, Centre of Excellence of Fidelity Investments. Additionally, I am a researcher at the Computer Science & Engineering department of Jadavpur University, India. Before this, I worked for Times Internet (digital wing of The Times Group) and MathLogic (an AI consulting startup). My research interests include Industrial Applications of Natural Language Processing, Large Language Models, and GenAI. Now my mission is to demystify financial texts for social good.
Here is my CV.
In addition to being a US patent holder, co-author of the books Natural Language Processing Fundamentals and The Natural Language Processing Workshop, I have several publications in international venues of repute, such as ACM TheWebConf (WWW), ACM CIKM, COLING, LREC, IEEE BigData, ACM CODS-COMAD and so on. I hold a Master’s Degree in Software Systems (with specialization in Data Analytics) from BITS Pilani, India and a Bachelor’s Degree in Computer Science and Engineering from HIT-K.
Outside work, I like traveling and playing harmonica. Being an adventure lover and a fitness buff, I believe that “Health is Wealth”.
Selected News and Updates
| Jul 2024 | My paper, "Demystifying Financial Texts Using Natural Language Processing" got accepted at CIKM-2024 (pre-print) |
| Jul 2024 | Our US patent (No. 12033162), "Automated analysis of customer interaction text to generate customer intent information and hierarchy of customer issues" got granted (link) |
| Mar 2024 | Our paper, "Generator-Guided Crowd Reaction Assessment" got accepted at TheWebConf (WWW) 2024 (pre-print) |
| Feb 2024 | Our paper, "IndicFinNLP: Financial Natural Language Processing for Indian Languages" got accepted at LREC-COLING 2024 (paper) |
| Jan 2024 | Received Eureka Enablers (Eureka Innovation Awards 2023) from Fidelity Investments |
| Summary 2023: | Promotion@Fidelity. Publications: CODS-COMAD (India), FinNLP@IJCNLP-AACL (Indonesia), NTCIR (Japan), FIRE (India), IEEE Big Data (Italy), SNCS (Springer), Science Talks (Elsevier). Completed PhD coursework at Jadavpur University. |
| Aug 2023: | My Google Scholar profile reached 100 citations. Miles to go! |
| May 2023: | Received On the Spot (India) award from Fidelity Investments. |
| Jan 2023: | Presented two research papers at CODS-COMAD 2023, IIT-Bombay, India. Received honourable mention in the YRS track. |
| Jan 2023: | Promoted to the post of Senior Data Scientist at Fidelity Investments |
| Summary 2022: | Published research papers in FinNLP@EMNLP (UAE), FNP@LREC (France), FinWeb@WWW (France), NTCIR (Japan), FinNLP@IJCAI-ECAI (Austria), FIRE (India), IJIT (Springer), Software Impacts (Elsevier), Frontiers in AI. Filed a US patent. Registered at Jadavpur University. |
| Nov 2022: | Our papers, "FLUEnT: Financial Language Understandability Enhancement Toolkit" and "Using Natural Language Processing to Enhance Understandability of Financial Texts" got accepted at 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD-2023), Mumbai, India. (pre-print paper-1) (pre-print paper-2) |
| Oct 2022: | Our paper, "Evaluating Impact of Social Media Posts by Executives on Stock Prices" got accepted at the 14th meeting of Forum for Information Retrieval Evaluation (FIRE-2022), Kolkata, India. (pre-print) |
| Jun 2022: | Virtually presenting our research paper, FinRAD: Financial Readability Assessment Dataset - 13,000+ Definitions of Financial Terms for Measuring Readability at the Financial Narrative Processing workshop of LREC 2022, Marseille, France. |
| Mar 2022: | Our paper FiNCAT: Financial Numeral Claim Analysis Tool got accepted at FinWeb (collocated with ACM-The Web Conference-2022) (pre-print) (code) (demo) |
| Summary 2021: | Published research papers in SDPRA@PAKDD (India), FinNLP@IJCAI (Canada), FNP (UK), ICCMDE (India), ICON (India). Delivered a talk on Data Visualization at XIM, University, India. Filed a US patent. |
| Summary 2020: | Co-authored the book The Natural Language Processing Workshop (Packt publishing, UK). Published research papers in ACAI (China), IJIT (Springer). Got promoted to the post of Data Scientist at Fidelity Investments (effective from Jan 2021). |
| Summary 2019: | Graduated from BITS, Pilani (India) with Masters in Software Systems. Co-authored the book Natural Language Processing Fundamentals (Packt publishing, UK). Joined Fidelity Investments as a Senior Analyst. |
| Earlier: | Worked for Times Internet & MathLogic as Data Scientist & Analyst respectively. Graduated from HIT-K with B.Tech in Computer Science & Engineering. Qualified GATE. Published research papers in ISSE (Springer), ICACNI (Springer), ICACCE (IEEE), etc. |