Pluto7: Using machine learning to accurately predict demand
About Pluto7
Pluto7 is a technology solutions provider focused on machine learning and artificial intelligence for supply chains. The company’s Planning In A Box is a supply chain analytics application for small and midsized businesses that sell on Amazon, Shopify, and other online and offline channels. The software as a service (SaaS) uses machine learning to provide the most accurate inventory forecasts.
Tell us your challenge. We're here to help.
Contact usPluto7 Planning In A Box improves demand forecast accuracy by leveraging Google Machine Learning Engine and enhances system performance and reliability with Google Cloud Platform as its foundation.
Google Cloud Platform Results
- Delivers the most accurate demand forecasts to retailers
- Enables company to focus on new features and product development, instead of production problems
- Builds new features, such as chatbots, in one day instead of many
- Grows business by leveraging a reliable, scalable platform to deliver greater value
Significantly improves accuracy of demand forecasts
As a seller on Amazon, how do you accurately predict demand for your products to help ensure you have just the right amount of available inventory when it’s needed? If you buy more inventory than demand warrants, you lose money. Didn’t buy enough product to meet demand? You lose money in that scenario, too. And if you play it safe by regularly carrying low inventories, your ranking on Amazon could get pushed down—making it harder for potential customers to find you.
Solving the inventory dilemma is what Pluto7 Planning In A Box does for its small and midsized retail customers. The software as a service (SaaS) offering helps sellers on Amazon, Shopify, eBay, and other online channels accurately forecast demand weeks and months in advance to manage inventories accordingly.
Before 2017, Planning In A Box used a SQL database running on a cloud-based machine learning (ML) server to provide its service to customers, but server crashes were a problem. Demand forecast data was delivered as statistical averages, which were helpful but not as precise as desired. And, the solution couldn’t scale easily or cost effectively.
Planning In A Box engineers knew they needed to evolve the solution’s back-end system in order to grow and stay competitive. So, in early 2017, the Planning In A Box team began migrating to Google Cloud Platform. The team was particularly interested in discovering how Google Cloud Machine Learning Engine could help deliver the most accurate demand forecasts to the company’s retail customers.
Since Google Cloud Platform deployment was completed in Q2 2017, Planning In A Box customers have already experienced the benefits of more accurate forecasts—notably during a recent busy holiday shopping season. For example, using Google Cloud Machine Learning Engine and other services, Planning In A Box delivered a forecast in August to one of its customers, an Amazon seller specializing in kites. The forecast predicted demand for the seller’s kites would increase nearly 300% during the holiday season.
Based on that prediction, the seller geared up its manufacturing and inventory months in advance to prepare for the holiday demand. Because the forecast was extremely accurate, as well as delivered well in advance, the seller maximized revenues for a shopping season that is notoriously difficult to predict.
“The drive toward Google Cloud Platform was to get beyond performance bottlenecks and leverage Google machine learning on a cloud platform that scales and is cost effective.”
—Salil Amonkar, COO and AI/ML Professional Services Leader, Pluto7Significantly improving accuracy
Behind the scenes of the Planning In A Box offering, multiple Google services, including Google Kubernetes Engine, Google Cloud SQL, and Google BigQuery, “work together seamlessly to automate demand forecasting using a growing amount of datasets, while delivering increasingly detailed reporting analytics and more,” notes Salil Amonkar, COO and AI/ML Professional Services Leader for Pluto7.
Planning In A Box is built on a Docker container model and uses Google Kubernetes Engine to deploy the SaaS as images to customers. As a result, users can access the SaaS front end, as well as applications that run in their own environment on the back end, as separate instances—which helps them avoid the drawbacks of a multi-tenant environment.
“The drive toward Google Cloud Platform was to get beyond performance bottlenecks and leverage Google machine learning on a cloud platform that scales and is cost effective,” Salil adds.
The Planning In A Box team learned Google Cloud Platform quickly and were soon testing the level of demand forecasting accuracy in a Proof of Concept, adding more datasets to the machine learning model. Using a time-series forecasting model, forecast accuracy was significantly improved, especially compared to the statistical average forecasts the company’s previous solution provided.
“Google Cloud Platform is far more reliable than the previous platform Planning In A Box ran on, which would crash periodically,” says John Nikhil, Head of Growth & Sales, Planning in a Box, Pluto7. “We’d have to restart the server, get the data back in, and then do the forecasts again, and it was a drain on our resources that required two data scientists to keep the machine learning server running.” Having to re-input data after a crash could also affect the accuracy of forecasts.
Google Cloud Machine Learning Engine continuously “works around the clock, it never crashes,” John adds. As a result, he says forecast data can be requested at any time. “And because it doesn’t crash, I don’t have to worry about the data being incorrect.”
“It was so easy to deploy and test Google Cloud Machine Learning Engine without making any commitments or investments, especially since Google sweetens the deal with a credit for trying its services.”
—John Nikhil, Head of Growth & Sales, Planning in a Box, Pluto7From maintenance to development
Freed from dealing with production issues, Planning In A Box data scientists now focus on getting more relevant datasets into the ML model, to provide customers with a greater variety of insights—and by extension, give customers more options for viewing inventory data. For example, in the past, forecasts were SKU-based. “Now, we can do forecasts on a product segment basis, which can group multiple SKUs together,” John says.
The data scientists have also been able to focus on building new features. There are plans to release a real-time sentiment analysis add-on feature based on Google Cloud Natural Language to help retail customers more accurately determine which products to focus their sales efforts on, if they need to add new products, and more.
“To keep growing, we need to add new features. Google Cloud Platform lets us free up engineering resources so we can deliver greater value to customers.”
“To keep growing, we need to add new features,” John says. “Google Cloud Platform lets us free up engineering resources so we can deliver greater value to customers.”
—John Nikhil, Head of Growth & Sales, Planning in a Box, Pluto7Planning In A Box also uses Google Cloud Machine Learning to predict demand. “It’s a selling point for us,” John says. “It gets new customers in front of me for a demo, because they’re curious to see what Google machine learning can do for them.”
Along with Google Cloud Platform enabling more time for development, it also encourages experimentation, which is a compelling combination. The Planning In A Box team can easily experiment with Google Cloud Platform services, given the flexible pricing structure and free trials from Google. “It was so easy to deploy and test Google Cloud Machine Learning Engine without making any commitments or investments,” he says, “especially since Google sweetens the deal with a credit for trying its services.”
The Planning In A Box team has also experimented with Google Dialogflow Enterprise Edition for building chatbots. “With any other chatbot development software, I’d have had to pay for it,” John says, “and the experiment might not have worked. The ability to experiment without risk is one of the things I like most about Google Cloud Platform.” He adds that his developers deployed a chatbot in one day using Google Dialogflow Enterprise Edition, a process that would otherwise have taken at least several days.
Everything in a box
The freedom to experiment, along with the stability, scalability, cost-effectiveness, and breadth of services available in Google Cloud Platform, are encouraging Pluto7 to expand its vision of Planning In A Box services. The goal is to serve as a total inventory management solution, giving customers a full view of their inventory in warehouses, manufacturing, and stores, and integrating all their online channels, including Amazon (in the United States and internationally), Shopify, and eBay.
“We want them to see, at the click of a button, their complete inventory across the world, including the ability to manage their distribution, all in one place,” John says. Or, as the product name implies, to truly have all their "planning in a box."
Tell us your challenge. We're here to help.
Contact us
About Pluto7
Pluto7 is a technology solutions provider focused on machine learning and artificial intelligence for supply chains. The company’s Planning In A Box is a supply chain analytics application for small and midsized businesses that sell on Amazon, Shopify, and other online and offline channels. The software as a service (SaaS) uses machine learning to provide the most accurate inventory forecasts.