The repo enables accurate customer revenue forecasting using ARIMA and other time series methods. It provides practical examples, data preprocessing, evaluation, and optimization. It also identifies potential customers through market analysis and predictive modeling. Empowering businesses for data-driven growth.
Use generative AI techniques to train on the internal Red Hat customer revenue data and produce synthetic public datasets that can be used for model training.
Implement a public facing dashboard to visualize the model insights and results. Replicate our internal looker studio dashboard for the model trained on public datasets.
Creation of a notebook that demonstrates time series forecasting techniques using a publicly available dataset. This notebook aims to replicate our internal work while ensuring no confidential information is shared. The goal is to contribute to the open-source community and facilitate learning in time series forecasting.
Currently, we are using internal customer data to train the growth model, we should look for alternate publicly available datasets that we can use to train the model. This will be useful for showcasing the work to external forums such as in conferences, blog posts etc.
Create a blog post that explores the intersection of predictive analytics, AI, and ML technologies in fostering customer growth. This post aims to showcase the potential of leveraging these advanced techniques for gaining insights, making data-driven decisions, and enhancing customer acquisition and retention strategies. The blog post aims to provide practical insights and guidance to businesses seeking to utilize AI/ML predictive analytics for sustainable customer growth.