17543239. FACILITATING USER SELECTION USING TREND-BASED JOINT EMBEDDINGS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

FACILITATING USER SELECTION USING TREND-BASED JOINT EMBEDDINGS

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Satyam Dwivedi of Bangalore (IN)

Vijay Ekambaram of Chennai (IN)

Kushagra Manglik of Lucknow (IN)

Nupur Aggarwal of Bangalore (IN)

Vikas C. Raykar of Bangalore (IN)

FACILITATING USER SELECTION USING TREND-BASED JOINT EMBEDDINGS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17543239 titled 'FACILITATING USER SELECTION USING TREND-BASED JOINT EMBEDDINGS

Simplified Explanation

The abstract describes a method, system, and computer program for helping users select items from an online catalog using trend-based joint embeddings. Here are the key points:

• The method involves obtaining a user's selection of an item from an online catalog.
• A trend-based machine learning model is used to determine a compatible item based on the selected item and previously selected items by the user.
• The machine learning model is trained on historical data associated with the items in the catalog and fine-tuned using current trend data from multiple sources.
• Feedback is received from the user regarding the compatible item, which helps identify attributes related to the item.
• The machine learning model is then used to determine additional compatible items based on these attributes.

Potential applications of this technology:

• E-commerce platforms can use this method to provide personalized recommendations to users, improving their shopping experience.
• Online streaming services can use this method to suggest related content to users based on their previous selections, enhancing their entertainment experience.
• Travel booking websites can utilize this method to offer tailored suggestions for accommodations, flights, and activities based on users' preferences.

Problems solved by this technology:

• This technology addresses the challenge of providing accurate and relevant recommendations to users in a vast online catalog.
• It solves the problem of understanding user preferences and identifying compatible items based on their previous selections.
• It helps overcome the limitations of traditional recommendation systems by incorporating trend-based machine learning models.

Benefits of this technology:

• Users can discover new items that align with their interests and preferences, leading to a more satisfying shopping or browsing experience.
• Businesses can increase customer engagement and sales by offering personalized recommendations that match users' tastes.
• The use of trend-based machine learning models allows for real-time adaptation to changing trends, ensuring up-to-date and relevant recommendations.

Original Abstract Submitted

Methods, systems, and computer program products for facilitating user selection using trend-based joint embeddings are provided herein. A method includes obtaining a selection of an item in an online catalog; determining a compatible item of the plurality of items at least in part by providing the selected at least one item and at least one previously selected item corresponding to the user to a trend-based machine learning model, wherein the trend-based machine learning model is trained on historical data associated with the item in the online catalog and fine-tuned based on current trend data from multiple data sources; receiving feedback in response to outputting the at least one compatible item; identifying one or more attributes related to the at least one compatible item based on the feedback; and using the trend-based machine learning model to determine at least one additional compatible item based on the one or more attributes.