Demand Forecasting Case Study: Parcel Delivery

Addepto team built and implemented a Machine Learning prediction model based on the historical data, macroeconomics factors, and other 3rd party data with rare events such as Covid included.

LLM-based Assistance Bot to enhance airport operations

Addepto's team developed a cloud-based solution leveraging GPT-4, LLamaIndex, and advanced Face Recognition algorithms. This enables the system to provide human-like responses by utilizing the RAG (Retrieval-Augmented Generation) approach in fine-tuning LLMs.

Text Summarization with the OpenAI API

The general eBook summary is just the starting point of our solution. To ensure users find it valuable, we designed a feature that generates a quiz-like series of control questions based on the summary. This "quiz" helps users extract key information, enabling them to better understand and grasp the essence of the text.

Advanced AI System for Seamless Bottle Recycling

The primary challenge was developing and integrating an accurate, high-performing AI model capable of identifying objects entering the machines, incorporating anti-fraud mechanisms, and ensuring the entire system operated smoothly on an internal software setup running on Raspberry Pi.

Implementing an MLOps Platform for Seamless Transition from Concept to Deployment

The Addepto platform simplified the deployment process, reduced inconsistencies between development and production environments, and sped up the shift from concept to large-scale production. This method not only enhanced workflow efficiency but also enabled the Client’s Data Science Team to concentrate on building advanced AI models ready for immediate real-world use.