Intellectual Property India Publishes Patent Application for 'Automatic Detection Of Spam Products Using Machine Learning' Filed by Jennifer D; Dr. M. S. Vinmathi; Mrs. R. Rajeshwari; Ms. Sivadharshini R K; Ms. Drucilla Sheryl Malvina I; Ms. Vaishnavi N; Mr. M. Maheswari; Dr. K. Sangeetha; Mrs. Marybenita; and Mr. Sathya L

MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641051180 A) filed by Jennifer D; Dr. M. S. Vinmathi; Mrs. R. Rajeshwari; Ms. Sivadharshini R K; Ms. Drucilla Sheryl Malvina I; Ms. Vaishnavi N; Mr. M. Maheswari; Dr. K. Sangeetha; Mrs. Marybenita; and Mr. Sathya L, Chennai, Tamil Nadu, on April 22, for 'automatic detection of spam products using machine learning.'

Inventor(s) include Jennifer D; Dr. M. S. Vinmathi; Mrs. R. Rajeshwari; Ms. Sivadharshini R K; Ms. Drucilla Sheryl Malvina I; Ms. Vaishnavi N; Mr. M. Maheswari; Dr. K. Sangeetha; Mrs. Marybenita; and Mr. Sathya L.

The application for the patent was published on May 29, under issue no. 22/2026.

According to the abstract released by the Intellectual Property India: "The rapid growth of e-commerce platforms has led to an increase in fraudulent activities such as spam products, fake reviews, and manipulated ratings, which negatively affect customer trust and platform reliability. Traditional detection methods are often inefficient due to the large volume and dynamic nature of online data. To address this issue, the proposed system presents an automated spam product detection solution using machine learning techniques.The system collects product-related data including descriptions, reviews, ratings, and seller information, and processes the data through preprocessing and feature extraction techniques. It utilizes supervised machine learning algorithms such as Naive Bayes, Support Vector Machine (SVM), Logistic Regression, and Random Forest to classify products as spam or genuine. The system also supports real-time analysis and identifies spam indicators such as fake reviews, abnormal rating patterns, and misleading product descriptions.The performance of the system is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure effective detection. The proposed solution reduces manual effort, improves detection accuracy, and enhances the integrity of e-commerce platforms. Overall, the system provides a reliable and scalable approach for identifying fraudulent product listings and improving user trust in online shopping environments."

Disclaimer: Curated by HT Syndication.