Using machine learning models for the energy and grid sector involves applying various forecasting techniques within these models to create a high-quality forecasting dashboard. This enables the grid management team to accurately predict electricity consumption patterns, ensuring an adequate and efficient energy supply for consumers.

-Employed advanced text classification algorithms within the Microsoft Sprinklr platform.- Utilized Boolean queries to filter and analyze comments from various social media platforms, including Facebook, Twitter, and Instagram.- Incorporated sentiment analysis techniques to gauge public perception and sentiment towards specific topics or brands. Established direct communication channels with Microsoft for query submission and verification, ensuring accuracy and reliability in the analysis process. -Collaborated with Microsoft's team to fine-tune queries and optimize classification models for improved performance and accuracy.

-Dealing with the machine learning component.-Training machine learning models with integrated neural networks- Utilization of LLM models, including the recent BERT LLM. Implementation of deep learning projects, such as image classification.- Deployment of Quantum Convolutional Neural Networks for image preprocessing