Walmart has patented a system to identify fraudulent transactions using a modified strategy based on historical transaction data. The system trains a classifier engine, applies discrete stochastic gradient descent algorithms, and updates strategies to determine fraud probability. This innovative approach aims to enhance fraud detection in retail transactions. GlobalData’s report on Walmart gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Walmart, Transaction splitting was a key innovation area identified from patents. Walmart's grant share as of April 2024 was 38%. Grant share is based on the ratio of number of grants to total number of patents.
Fraudulent transaction identification system using machine learning
A recently granted patent (Publication Number: US11995659B2) discloses a system that utilizes historical transaction data to detect fraudulent activities in customer returns. The system comprises a communications interface, a database storing historical transaction data, and a computing device that trains a classifier engine with the historical data. The system generates an initial strategy based on class data and fraud probability data, which is then modified using a discrete stochastic gradient descent (DSGD) algorithm to create a more comprehensive strategy. The modified strategy is used to update the training examples, re-train the classifier engine, and generate fraud data to identify fraudulent returns by customers.
Furthermore, the patent details a computer-implemented method and a non-transitory computer-readable medium with instructions for training the classifier engine, generating strategies, applying DSGD algorithms, updating training examples, re-training the classifier engine, and identifying fraudulent returns based on classifier data. The method and medium also emphasize the use of feature data, such as return amounts and receipt information, in determining fraudulent activities. The DSGD algorithm plays a crucial role in modifying thresholds and rules within the strategies to enhance fraud detection capabilities. Overall, the patented system aims to improve fraud detection in customer returns by leveraging historical transaction data and advanced algorithms for strategy modification and training.
To know more about GlobalData’s detailed insights on Walmart, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
