Morgan Stanley has patented a system for analyzing handwritten text to detect fraudulent activity. The technology uses feature extraction and clustering to identify mismatches between purported and actual writers. If a sample is flagged as potentially fraudulent, the system alerts users to prevent further deception. GlobalData’s report on Morgan Stanley 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 Morgan Stanley, Retail trading platforms was a key innovation area identified from patents. Morgan Stanley's grant share as of April 2024 was 91%. Grant share is based on the ratio of number of grants to total number of patents.
Automated analysis of handwritten text for fraud detection
A recently granted patent (Publication Number: US11961094B2) outlines a system designed to automatically analyze handwritten text to identify discrepancies between the purported writer and the actual writer. The system includes a text sample database, processors, and memory storing instructions for executing various tasks. These tasks involve receiving digitized handwriting samples associated with different individuals, extracting features from the samples, clustering vectors based on similarity, and determining the likelihood of fraud based on metadata analysis. If a mismatch is detected, the system flags additional samples entered by the individual in question as potentially fraudulent.
Furthermore, the system can compute similarity scores between additional samples and existing ones, report potential fraud based on predetermined thresholds, and even communicate with a workflow management server to require authorization for workflows involving potentially fraudulent signatures. The metadata stored includes indicators of semantic content or function of handwritten text, such as signatures. The determination of potential fraud is aided by a convolutional neural network classifier, and the extracted features for analysis include histograms of oriented gradients, energy-entropy comparisons, and Pearson coefficients between waveforms. Overall, this system offers a comprehensive approach to automatically analyzing handwritten text for writer verification and fraud detection.
To know more about GlobalData’s detailed insights on Morgan Stanley, 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.
