Embedded Files
By utilizing historical borrower data, the model will classify applicants as likely to default or not, enabling banks to make informed lending decisions and minimize potential losses.
Loan-default Prediction
Banks earn a major revenue from lending loans. But it is often associated with risk. The borrowers may default on the loan. To mitigate this issue, the banks have decided to use Machine Learning to overcome this issue. They have collected past data on the loan borrowers & would like you to develop a strong ML Model to classify if any new borrower is likely to default or not.
This project aims to develop a machine learning model that helps banks predict loan default risk for new applicants.
Short-Term Energy Demand Forecasting
This case study addresses the challenge of short-term energy demand forecasting using hourly electricity consumption data. The objective is to generate accurate one-day-ahead forecasts to support operational decisions in energy supply and trading.
Several time series models were evaluated, including:
ETS (Exponential Smoothing) as a baseline,
SARIMA for handling trend and seasonality,
RNN with LSTM layers for capturing nonlinear temporal patterns.
Model selection and preprocessing were guided by exploratory data analysis. An additive ETS model with damped trend and daily seasonality was chosen based on observed patterns. Differing techniques were applied to achieve stationarity, improving model interpretability and performance.
Forecast accuracy was evaluated using RMSE, MAE, and MAPE. A rolling-origin evaluation with stepped windows was used for efficient, realistic validation. The study highlights the effectiveness of simple, well-structured models and points to future improvements through external data integration and deeper model tuning.
This dashboard is intentionally lightweight: it’s designed for development and validation, allowing you to submit video links, inspect transcripts, review extracted facts, and see generated itineraries, rather than serving as a polished user-facing product.
Itinerary Planner Agent
AI Trip Planner Core is a FastAPI backend that turns travel videos into structured trip plans. It ingests YouTube links, transcribes spoken captions using yt-dlp and faster-whisper (with graceful fallback to video titles and descriptions when audio is unavailable), and then runs a two-step OpenAI pipeline: first extracting concrete travel facts (places, timing, costs, activities), and then synthesizing those facts into a coherent, day-by-day itinerary.
All intermediate and final results are cached and versioned in PostgreSQL, making it easy to rerun prompts, compare outputs, and iterate on extraction logic without recomputing everything from scratch. A CORS-enabled async API supports programmatic submission and retrieval of runs, while a minimal HTML dashboard provides a practical way to test the system end-to-end.
Page updated
Google Sites
Report abuse