17823130. Using a Trained Neural Network to Standardize User Product Ratings on Online Systems simplified abstract (International Business Machines Corporation)

Using a Trained Neural Network to Standardize User Product Ratings on Online Systems

Organization Name

International Business Machines Corporation

Inventor(s)

Shikhar Kwatra of San Jose CA (US)

Vijay Ekambaram of Chennai (IN)

Anvita Vyas of Madhya Pradesh (IN)

Jeremy R. Fox of Georgetown TX (US)

Using a Trained Neural Network to Standardize User Product Ratings on Online Systems - A simplified explanation of the abstract

This abstract first appeared for US patent application 17823130 titled 'Using a Trained Neural Network to Standardize User Product Ratings on Online Systems

Simplified Explanation

The abstract describes a method using a trained neural network to standardize user ratings for products based on historical data.

• Neural network trained to generate attribute-based leniency and strictness rating scores for product attributes.
• Overall leniency and strictness rating score determined for a product based on attribute scores.
• User rating of product adjusted using overall rating score to create standardized user rating.

• • Potential Applications:**
• E-commerce platforms can use this technology to provide more accurate and consistent product ratings to customers.
• Market research companies can utilize this method to analyze user preferences and trends in different product categories.

• • Problems Solved:**
• Inconsistencies in user ratings due to individual leniency or strictness can be minimized.
• Helps in comparing and evaluating products within the same category more effectively.

• • Benefits:**
• Improves user experience by providing standardized ratings for products.
• Enhances decision-making for consumers by offering more reliable information on product quality.

Original Abstract Submitted

Using a trained neural network to transform user ratings into standardized user ratings is provided. Respective attribute-based leniency and strictness rating scores are generated for a plurality of attributes associated with a product category using the trained neural network based on historical user ratings of products in the product category. A set of attributes associated with a product included in the product category is identified. An overall leniency and strictness rating score is determined for the product using the trained neural network based on a set of attribute-based leniency and strictness rating scores for the set of attributes associated with the product included in the product category. A user rating of the product is received. The user rating of the product is adjusted based on the overall leniency and strictness rating score for the product included in the product category to form a standardized user rating for the product.