Active
Projects
Text-To-SQL
Lifted valid SQL from ~38% to ~77% with ~83% execution accuracy across 11 cross-domain Spider databases.
PythonPostgesqlFlanT5Fine TuningPrompt EngineeringFastAPIStreamlit
LLMind
FinBERT led on MSFT (R² = 0.97), Claude topped untuned models on AAPL/AMZN (R² = 0.88) — showing domain fine-tuning beats model size.
ChatGPTDeepSeekFinBertClaudePythonPrompt Engineering
Stack & AI tools
OpenAI APILangChainGeminiClaudeCursorGitHub CopilotLlamaRAGReact JSFlanT5FinBertPythonSQLJavaAWSGCP DLPPostgesqlHugging FaceLLMTransformers