Enterprise Response Time Prediction via Causal Variable Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for predicting enterprise system response time are theoretical and lack practical application, failing to accurately predict performance due to complexity and inability to adapt to real-time decision-making, especially in large-scale systems.
Innovation Solution
A method and system that preprocess historical output time series data to select significant causal variables and derive dummy variables using regression techniques and threshold-based methods, then train predictive models using machine learning techniques to forecast response time, enabling advanced prediction and preventive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional prediction techniques are used, then the prediction process is simple, but the prediction accuracy of enterprise system response time is low
Solution Approach 1:
The patent segments the prediction process into multiple distinct modules: data preprocessing module, feature engineering module (creating dummy variables for peaks and troughs), model training module, and prediction module. This segmentation allows each module to be optimized independently, achieving high prediction accuracy while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The patent implements dynamic adaptation by selecting different machine learning models and hyperparameters based on the characteristics of the input data. The system dynamically adjusts the prediction approach by analyzing data patterns and selecting appropriate models, thereby achieving high accuracy across varying system conditions without requiring a single complex fixed model.
2Adaptability or versatility
If theoretical prediction solutions are applied, then the implementation is straightforward, but the practical applicability to real enterprise systems is limited
Solution Approach 1:
The patent transforms theoretical prediction solutions into practical applications by changing key parameters: it uses real enterprise system data with actual operational characteristics, applies industry-specific feature engineering (peak/trough detection for system performance), and selects models optimized for production environments. This allows the solution to adapt to real-world complexity while maintaining implementation feasibility through systematic methodology.
Solution Approach 2:
The patent introduces intermediary components that bridge theoretical models and practical application: feature engineering intermediaries that transform raw enterprise data into meaningful predictors, and preprocessing intermediaries that handle real-world data quality issues. These intermediaries make theoretical solutions practically applicable without requiring complete redesign.
3Loss of time
If periodic and concurrent measurements are taken, then the data collection is simple, but the ability to predict response time in advance is insufficient
Solution Approach 1:
The patent applies preliminary action by using feature engineering to identify and flag peak and trough periods in advance based on historical patterns. The model learns from past peak/trough characteristics and applies this knowledge to predict future response times before they occur, providing advance warning while maintaining prediction accuracy through pattern recognition rather than reactive measurement.
Solution Approach 2:
The patent adds temporal dimensionality by creating dummy variables that capture the timing and duration of peak and trough periods. This transforms simple periodic measurements into rich temporal features that enable the model to predict response times in advance by recognizing temporal patterns, thereby gaining prediction lead time without sacrificing accuracy.
Data Source
AI summary
System and method for predicting enterprise system response time is disclosed. System pre-processes causal variables of historical output time series data to select subset of causal variables by applying regression techniques to obtain significant causal variables. Historical output time series data shows response time of enterprise system. System derives dummy variables from historical output time series data using threshold based method. Dummy variables are specific to peak detection and trough detection in historic output time series data. System trains predictive model using historical output time series data, significant causal variables, and dummy variables to generate trained predictive model and predictive model designed using machine learning technique selected based on forecast methodology used for forecasting input time series data. System predicts enterprise system response time by using trained predictive model, input time series data or lag between input time series data and historical output time series data.