Conversion Rate Prediction Using Multi-Task Ad Conversion Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Selecting advertisements for transmission to diverse devices and locations in a digital world is challenging due to the difficulty in predicting conversion rates effectively.
Innovation Solution
An advertising system uses a machine learning model trained on multi-task learning to predict conversion rates based on pixel events and click-through and view-through conversions, applying inverse propensity weighting to select advertisements for display on end-user devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional advertisement selection methods are used, then the system is simple to operate, but the conversion rate prediction accuracy is low
Solution Approach 1:
The patent introduces a machine learning model as an intermediary component between the advertisement selection system and the conversion rate prediction task. This model processes pixel events and bid features to generate accurate conversion rate predictions without requiring complex manual analysis or manual intervention in the core selection logic
Solution Approach 2:
The patent replaces traditional mechanical or manual advertisement selection methods with an automated machine learning-based system. The model automatically processes features, predicts conversion rates, and supports decision-making, substituting manual analysis and simplifying the operational complexity despite the advanced algorithms used
2Measurement precision
If multiple conversion metrics are considered, then the advertisement selection accuracy is improved, but the data processing complexity increases
Solution Approach 1:
The patent merges multiple conversion metrics (click-through conversions, view-through conversions, pixel events) into a unified machine learning model. The model integrates these diverse data sources and processes them together to generate a single conversion rate prediction, simplifying the handling of multiple metrics while maintaining high accuracy
Solution Approach 2:
The machine learning model serves multiple functions: it processes pixel events, evaluates click-through conversions, assesses view-through conversions, and generates conversion rate predictions all within a single system. This multi-functionality reduces the need for separate processing systems for each metric
Data Source
AI summary
Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for predicting a conversion rate. The program and method provide for receiving, from an advertisement service, a bid to display a first advertisement at a computing device; determining, in response to receiving the bid, a set of features that relate to the first advertisement; providing the set of features to a machine learning model configured to output a predicted conversion rate for the first advertisement, the machine learning model having been trained based on multi-task learning using plural sets of features corresponding to plural second advertisements, the plural sets of features being associated with both click-through conversions and view-through conversions; and determining, based on the output of the machine learning model with respect to the set of features, the predicted conversion rate for the first advertisement.