This project focuses on automating inventory management in warehouses by predicting future stock requirements and analyzing sentiment from news articles to adjust predictions accordingly. The model optimizes space utilization, tracks trends, and evaluates sentiment to ensure efficient stock management.
- Space Utilization Optimization: Predicts future stock requirements, enabling owners to restock only the predicted amount based on urgency.
- Trend Analysis: Updates on trends and learns patterns from historical data, facilitating restocking of the most demanding stock.
- Sentiment Analysis: Analyzes real-time events affecting stock levels, predicting positive and negative scores for commodities and adjusting expected sales.
- Automated Inventory Management: Evaluates most demanding products, sends restocking alerts, and suggests desired quantities based on current requirements.
- Sentiment Analysis on News Articles: Analyzes news sentiment affecting stock levels.
- Data Preprocessing: Removes unwanted columns and rows from the dataset.
- Training GBR Model: Trains a Gradient Boosting Regressor (GBR) model for sale prediction.
- Predicting Stocks Required: Forecasts required stock quantities for optimal inventory management.
- Generating Alerts: Sends alerts for restocking based on current requirements.
- Automating Inventory Management: Manages inventory based on current requirements.
- Historical Data Trained Model Using Deep Learning
- Trend Analysis effect on prediction
- Utilizes GBR algorithm for predicting future sales based on historical data and current warehouse conditions.
- Trained on a grocery dataset with 3000 entries, achieving 98% predictive accuracy.
- Forecasts required stock quantities for optimal inventory management.
- Employs NLP for sentiment analysis of news trends affecting commodity sales.
- Sentiment score(-1.0 to 1.0 scale) guides stock adjustment decisions .
- Assesses warehouse space availability for efficient stock allocation.