Product Portfolio Reduction via Data Lake Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In B2B ecommerce, large product portfolios lead to redundant recommendations and missed opportunities, as existing systems struggle to provide personalized experiences due to the vast number of products, resulting in inefficient resource usage and suboptimal customer engagement.
Innovation Solution
A system utilizing a data lake to aggregate customer activity data, analyze purchases, and reduce the product portfolio by identifying interdependent products, recommending related items based on customer behavior, and utilizing predictive analytics to rank products for optimal revenue coverage and customer goal alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a vast product portfolio is maintained, then product variety and customer choice are improved, but recommendation accuracy and system performance deteriorate due to redundant products and missed opportunities
Solution Approach 1:
The patent extracts and removes redundant products from the vast product portfolio by comparing product attributes and identifying duplicates or near-duplicates. This extraction process reduces the portfolio size while preserving the essential product variety, thereby improving recommendation accuracy without significantly reducing customer choice.
Solution Approach 2:
The patent segments the vast product portfolio into manageable groups or clusters based on product attributes, categories, and relationships. This segmentation allows the system to process and analyze products more efficiently, improving recommendation accuracy by focusing on relevant product subsets rather than the entire portfolio at once.
2Quantity of substance
If a vast product portfolio is processed, then comprehensive product coverage is improved, but resource usage and processing efficiency deteriorate
Solution Approach 1:
The patent extracts only the essential and non-redundant products from the vast portfolio for processing. By removing duplicate and unnecessary products before analysis, the system maintains comprehensive product coverage with a reduced dataset, significantly improving processing efficiency and resource utilization.
Solution Approach 2:
The patent performs preliminary processing actions by pre-computing product attributes, relationships, and redundancy indicators before the main recommendation process. This preliminary action reduces the complexity of subsequent processing steps, enabling faster and more efficient handling of the product portfolio while maintaining comprehensive coverage.
3Productivity
If product portfolio reduction is implemented, then recommendation quality and resource efficiency are improved, but product coverage and customer options may worsen
Solution Approach 1:
The patent carefully extracts only redundant products for removal, preserving all unique and valuable products in the reduced portfolio. This selective extraction ensures that product coverage and customer options are maintained at optimal levels while achieving the resource efficiency benefits of portfolio reduction.
Solution Approach 2:
The patent merges or consolidates redundant products into representative entries in the reduced portfolio, ensuring that the essential product coverage is preserved. By combining duplicates while maintaining the underlying product variety, the system achieves resource efficiency without sacrificing customer options or product coverage.
Data Source
AI summary
Examples described herein relate to a system consistent with the disclosure. For instance, the system may comprise a data lake including information relating to an in-store activity of a customer and an online activity of the customer, a processing resource, and a non-transitory machine-readable medium storing instructions executable by the processing resource to identify the in-store activity and the online activity of the customer, aggregate and store the in-store activity and the online activity of the customer in the data lake, reduce an amount of products in a product portfolio, compare purchases including in-store purchases and online purchases, and recommend a product of the plurality of products based on the comparison.