🤖 Hybrid Multilingual RAG + Ensemble Sentiment + Economic Forecast

No index built yet.

🎙️ Speak your question — get a spoken answer

🤖 Hybrid Multilingual RAG Framework

🔧 Models Used

• 🏦 FinBERT (ProsusAI) — Financial sentiment (40%)
• 🌍 XLM-RoBERTa (CardiffNLP) — Multilingual sentiment (30%)
• 📖 Economic Lexicon — Domain-specific keywords (30%)
• 🔍 MiniLM-L12 — Multilingual embeddings (FAISS)
• 📊 ms-marco-MiniLM — Cross-encoder reranking
• 🗣️ Whisper-small — ASR
• 🤖 Llama-3.3-70B via Groq — Response generation

📊 Forecasting

• Baseline: ARIMA(1,1,1)
• Enhanced: SARIMAX + Ensemble Sentiment (n_test = 3)
• Tests: ADF, Granger Causality, Diebold-Mariano
• Data: World Bank API

📈 Economic Forecast — ARIMA vs SARIMAX + Ensemble Sentiment

n_test = 3 — Evaluates on the last 3 years (captures recent economic turbulence)