Machine Learning Use Cases in Retail
simMachines supports use cases for retailers spanning insight-driven marketing, advertising and e-commerce applications.
Sales, Product Usage and Retention Forecasting
Problem
Top 3 retailer needs to be able to forecast product level sales, usage, and ongoing retention of customers who have purchased the product starting with the high end electronics category and associated VR products.
Challenge
SKU level analysis and forecasting requires machine learning technology to handle the volume of data and analyses/forecasts.
Solution
Similarity based machine learning enabled the trending of monthly product users by those predicted to churn vs. stay loyal to the product at a very granular level of machine generated customer segments.
Result
Client prioritizing SKU level products and data requirements to enable optimal forecasting.
Sales Forecasting and Customer Lifetime Value
Problem
Specialty retailer needed to calculate the future sales and lifetime value of customers.
Challenge
Client wanted a technology solution that could learn and adjust over time, as well as accurately predict and classify customers based on limited data.
Solution
The solution predicted future purchase volume and net income, as well as classified the customer base into groups based on value and the associated “Why” factors that define them.
Result
Predictions with 95% accuracy compared to ground truth demonstrate that the algorithm can provide an automated calculation of a new or existing customer’s future purchase volume, net profit and LTV.
eCommerce Retail Sales Tax Determination
Problem
International logistics firm needed to be able to perform online, real-time import tax determination for Amazon, eBay and other customers, dependent on the “ship to” country.
Challenges
For real-time determination of import tax to a wide range of countries based on a product type, machine learning tools were needed that could enable real-time calculations using historical data relevant to each country.
Solution
simMachines produced a distance function that identifies the similarity of items based on the same metrics as those used by a tariff officer. This allowed the tariff to be calculated for items that had never been sent to the target country in the past.
Result
Machine learning algorithm is currently providing accurate import taxes on 150,000 orders per day.
