Digital Ad Inventory Allocation via Segment Decompression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing advertising inventory on digital platforms is complex due to overlapping product segments and cannibalization issues, leading to revenue loss and inefficiencies in fulfilling contracts, as existing systems struggle to accurately forecast and allocate available ad space across multiple dimensions.
Innovation Solution
An inventory management system that decomposes historical data to create compressed representations of product vectors, allowing for enhanced forecasting and allocation techniques that minimize cannibalization by using logically necessary allocation methods, such as hierarchical and constraining set methods, to optimize ad space allocation across overlapping and hierarchically related segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If traditional advertising inventory allocation methods are used, then simplicity of operation is maintained, but cannibalization occurs and revenue is lost due to overlapping product segments
Solution Approach 1:
The patent segments advertising inventory into distinct electronic segments (e.g., video segments, audio segments, display segments) with unique identifiers. Each segment is treated as a separate allocable unit, allowing the system to track and allocate inventory without cannibalization across overlapping product segments. This segmentation enables precise control over which segments are allocated to which contracts.
Solution Approach 2:
The patent introduces a new dimension of segment identification by adding electronic segment identifiers to traditional advertising inventory. This creates a multi-dimensional allocation space where inventory can be distinguished not just by contract or product segment, but also by specific electronic segment characteristics. This additional dimension prevents cannibalization by enabling the system to allocate specific segments to specific contracts without overlap.
2Measurement precision
If detailed tracking of overlapping product segments is implemented, then allocation accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary decomposition of historical allocation data to create compressed representations of product vectors before actual allocation decisions are made. This pre-processing step organizes the data into a structured format that facilitates accurate forecasting while reducing the computational burden during real-time allocation. The compressed representations capture essential patterns without requiring full detailed tracking of all historical data.
Solution Approach 2:
The patent transforms the representation of advertising inventory by introducing electronic segment identifiers as new parameters. This parameter change enables the system to distinguish between overlapping segments that would otherwise be indistinguishable. By changing how inventory is represented (adding segment ID dimensions), the system achieves precise allocation tracking without requiring complex computational models to resolve overlaps.
3Productivity
If maximum ad space availability is ensured through sophisticated allocation, then revenue increases, but system complexity and data processing requirements increase
Solution Approach 1:
The patent extracts and separates the electronic segment identification information from the broader advertising inventory data. By isolating this key identifying information, the system can track and allocate segments efficiently without processing all the detailed attributes of each advertising impression. This extraction reduces data processing requirements while maintaining the ability to make sophisticated allocation decisions.
Solution Approach 2:
The patent performs preliminary decomposition of historical data to create compressed representations that capture essential allocation patterns. This pre-processing reduces the volume of data that needs to be processed during actual allocation operations, enabling sophisticated revenue-optimizing allocation without the full computational burden of processing all raw historical data in real-time.
Data Source
AI summary
Aspects of the subject disclosure may include, for example, receiving a request to forecast allocations for a new descriptor, the new descriptor differing from preexisting descriptors, each of the preexisting descriptors being associated with a subset of locations of a network of locations, each location corresponding to an electronic segment in electronic canvases, and the new descriptor being associated with a new subset of locations of the network of locations, identifying one or more affected descriptors having one or more overlapping subsets of locations of the network of locations and one or more non-overlapping subsets of locations of the network of locations, determining a forecast of allocated locations in each of the one or more affected descriptors; identifying, according to the forecast, at least a portion of allocated locations in the one or more overlapping subsets of locations that are displaceable resulting in a number of displaceable allocations, and determining, according to the number of displaceable allocations, a forecast of available unallocated locations with displacement. Other embodiments are disclosed.