ML Recommendation Network for Trusted Purchase Advice
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in making informed purchasing decisions due to overwhelming and unreliable online reviews, and often lack knowledge of which friends and family members have relevant purchasing experience with the asset they are interested in.
Innovation Solution
A machine learning model analyzes purchase intention, social networking, and purchase history data to identify and connect users who can provide valuable insights on intended purchases, prompting them to share their experiences with the potential buyer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If users rely on online reviews for purchasing decisions, then they can gather information from multiple sources, but the volume and reliability of reviews becomes overwhelming and unreliable
Solution Approach 1:
The system extracts and filters reliable information from the vast quantity of online reviews by using machine learning models to identify patterns, detect fake reviews, and select trustworthy customer feedback, thereby separating reliable insights from the overwhelming noise of unlimited reviews
Solution Approach 2:
The patent introduces an intermediary system consisting of machine learning models and recommendation algorithms that mediate between users and online reviews, automatically analyzing and filtering the information to present only the most reliable and relevant feedback to users
2Reliability
If users ask friends and family for advice, then they receive more reliable and valuable input, but users lack knowledge of which connections have relevant purchasing experience
Solution Approach 1:
The system performs preliminary analysis of users' social network connections and purchase histories before the user needs advice, pre-identifying and ranking potential knowledgeable connections based on their relevant purchasing experience, so that when advice is needed, the system can quickly present the most suitable connections
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously learns from users' interactions with recommended connections and adjusts its recommendations, while also allowing users to rate and provide feedback on the usefulness of advice received from different connections, improving future recommendations
3Loss of information
If users conduct extensive online research, then they can gather more information, but the purchasing process becomes more time-consuming
Solution Approach 1:
The system provides self-service by automatically performing the time-consuming tasks of analyzing purchase histories, evaluating connection relevance, and curating personalized recommendations, freeing users from manual research while still providing comprehensive information about potential purchases
Data Source
AI summary
Methods, systems, and apparatuses are described herein for providing purchase recommendations by analyzing social networks using machine learning. A machine learning model may be trained to select one or more of the first plurality of users. Purchase intention data that indicates an intention of a first user to acquire a type of asset may be received. Social networking data that comprises a plurality of associations between a second plurality of users may be received. Purchase history data indicating one or more purchases, of one or more assets associated with the type of asset, made by the second plurality of users may be received. The trained machine learning model may be provided the data. In return, the trained machine learning model may provide an indication of a second user. A notification may be sent to the second user.