Context Aware Auto-AI Framework

The field of artificial intelligence has made tremendous strides in recent years, with machine learning models being used in a wide range of applications. However, the performance of these models is often limited by the quality and quantity of the training data. Moreover, different contexts such as type of problem, problem domain and sub-domain, changes in the input data distribution for the particular type of problem and the task requirements, can significantly impact the model’s performance and the process of model’s performance tuning. To address these challenges, researchers have developed automated machine learning frameworks that can select and optimize machine learning models based on certain factors. We introduce a Context Aware Auto-AI framework that can identify and incorporate relevant contextual information into the model selection and optimization process, resulting in more accurate and effective models. This can also help reducing the time taken to arrive at the right hyperparameters. In this paper, we present a novel approach to automated machine learning that incorporates context awareness into the model selection and optimization process. We start off with a set of hyperparameters with a context based on the type of ML problem, and change it in accordance with the knowledge corpus. This approach significantly improves the model performance and saves time and resources spent in tuning the model, and making it suitable for the user context and domain.