Machine Learning Anomaly Detection for Pricing Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Retailers face challenges in identifying and correcting price and cost anomalies, which can lead to financial losses due to data entry errors or incorrect pricing, affecting profitability.
Innovation Solution
A system utilizing machine learning models trained on historical purchase order data to detect anomalies in price and cost updates, allowing or denying updates based on anomaly determination, and re-training the algorithm with detected anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual price and cost updates are allowed without verification, then operational efficiency is maintained, but pricing accuracy deteriorates due to data entry errors
Solution Approach 1:
The patent introduces an intermediary anomaly detection system that sits between the manual update process and the final pricing decision. This system uses machine learning models trained on historical purchase order data to automatically detect and flag anomalous price and cost updates, allowing legitimate updates to proceed while blocking erroneous ones, thus maintaining both accuracy and efficiency
Solution Approach 2:
The patent replaces the mechanical manual verification process with an automated machine learning-based anomaly detection system. Instead of relying on human reviewers to check each price update, the system uses trained algorithms to automatically identify anomalies, significantly improving operational efficiency while maintaining or enhancing pricing accuracy
2Measurement precision
If anomaly detection system is implemented, then pricing accuracy is improved, but device complexity increases due to machine learning models
Solution Approach 1:
The patent applies preliminary action by training the machine learning models in advance using historical purchase order data before deployment. The models are pre-trained to recognize normal pricing patterns and anomalies, so when price updates occur, the system can quickly evaluate them without requiring complex real-time analysis, thereby reducing operational complexity
Solution Approach 2:
The system implements self-service through automated anomaly detection and flagging without requiring manual intervention. The machine learning models autonomously evaluate price updates, flag potential anomalies for review, and can automatically reject clearly erroneous updates, reducing the need for complex human-in-the-loop verification processes
3Measurement precision
If machine learning model is re-trained with detected anomalies, then measurement precision is improved, but loss of time increases due to re-training process
Solution Approach 1:
The patent implements feedback by using detected anomalies to re-train the machine learning models, creating a continuous improvement loop. The system learns from actual anomalies encountered in production, progressively improving its detection accuracy over time. This feedback mechanism allows the system to adapt to new pricing patterns and anomaly types, enhancing precision while the iterative nature allows for manageable re-training cycles
Data Source
AI summary
This application relates to apparatus and methods for identifying anomalies within data, such as pricing data. In some examples, a computing device receives data updates and selects a machine learning model to apply to the data update. The computing device may train the machine learning model with features generated based on historical purchase order data. An anomaly score is generated based on application of the machine learning model. Based on the anomaly score, the data update is either allowed, or denied. In some examples, the computing device re-trains the machine learning model with detected anomalies. In some embodiments, the computing device prioritizes detected anomalies for further investigation. In some embodiments, the computing device identifies the cause of the anomalies by identifying at least one feature that is causing the anomaly.