Zoined: Enhancing Retail and Hospitality Analytics with Neptune

Zoined is a company that provides Retail and Hospitality Analytics as a cloud-based service for various roles from top management to manager level. The service collects sales data from stores and venues, including inventories, time and attendance, and visitor tracking systems, as well as webstores. The data is analyzed and presented in a visual format for business owners to get real-time, actionable insights for their business. Zoined's product allows businesses to filter and group their data easily, create custom views, and quickly grasp trends with charts and graphs. The company caters to retail and wholesale businesses, especially in the fashion, food retail, coffee shops, and restaurant sectors.

Zoined, a company offering cloud-based Retail and Hospitality Analytics, faced a significant challenge in tracking and managing experiments, especially with a small team of scientists and engineers. The company's data scientist, Kha, was solely responsible for the forecasting pipeline, making experiment tracking a tedious manual task. Kha was dealing with large data frames with forecasts that needed to be logged alongside their experiments. He also needed a way to visualize results for complete and intermediate experiments to enhance efficiency. The team initially tried using Splunk for experiment tracking, but it proved to be intimidating, difficult for visualizing logged values, and expensive. The next solution, MLflow, presented issues with hosting options, was compute-intensive, and had problems with auto scaling. It also made collaboration difficult as sharing experiments was not straightforward.

Kha needed a solution that was fully managed, easy to set up, could scale to large volumes of experiment logs and forecast dataset, was automated and fast, and could be customized and integrated with existing technologies. After some research, Kha found Neptune, which met all these requirements. Neptune was chosen as Zoined’s solution for logging experiment metadata because it was fully managed, fast, scalable, offered a better price to value ratio, had better charts and visualizations of experiments, could visualize all types of data regardless of size and structure, and had automated logging of hardware performance metrics.

• Neptune significantly improved Kha’s experimentation workflow. It solved the infrastructure problem that Zoined was facing, providing out-of-the-box and custom logging options. It made debugging of hardware consumption easier, which was a significant improvement over the previous solutions. Additionally, Neptune proved to be a more cost-effective solution than maintaining MLflow. Overall, Neptune met the requirements of Kha and proved to be a useful solution for Zoined.