Scholar
Rajan Das Gupta
Google Scholar ID: ipE0E-8AAAAJ
B.Sc in CSE (AIUB), M.Sc in CS (JU)
Citations & Impact
Citations
15
H-index
2
i10-index
0
Publications
11
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- 1. xFiTRNN: A hybrid model for financial sentence analysis, combining self-attention, linearized phrase structures, and a contextualized transformer-based RNN. It improves accuracy in sentiment classification while providing sentence-level explainability.
- 2. A deep learning and machine learning approach to predict neonatal death in the context of São Paulo. Using data from 1.4 million newborns, machine learning models like XGBoost, Random Forest, and LSTM were tested. LSTM achieved 99% accuracy.
- 3. Pattern Recognition Tasks with Personalized Federated Learning, PLOS ONE, 2025.
- 4. xFiTRNN: A hybrid self attent linearized phrase structured contextualized transformer based RNN for financial sentence analysis with sentence level explainability, Scientific Nature, 2024.
- 5. Large Language Models in Computer Science Education: A Systematic Literature Review, SIGCSE'26, 2024.
- 6. A deep learning and machine learning approach to predict neonatal death in the context of São Paulo, IJPHS, 2023.
Research Experience
- Over five years of academic experience and four years developing advanced machine learning solutions. His work focuses on elevating Large Language Models (LLMs), multimodal natural language processing, and improving interpretability in machine learning.
Education
- M.Sc in Computer Science, Jahangirnagar University
- B.Sc in Computer Science, American International University-Bangladesh
Background
- Rajan Das Gupta is an Adjunct Faculty and UX Researcher with experience in both Education and Technology. He was a Computer Science teacher at PlayPen and is currently a UX Researcher at Apex DMIT Ltd. Rajan specializes in Advanced AI, including Generative AI and Explainable AI, with over years of experience in Academia and Industry. His focus is on Natural Language Processing (NLP) and Machine Learning (ML), applying these technologies to real-world problems.
Miscellany
- Interests: Large Language Models (LLMs), Multimodal NLP, NLP for Social Good, Machine Learning Interpretability, Human AI Interaction
