Construction Software Usage Modeling for Project Performance Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing construction management software applications lack the ability to evaluate a party's usage of their software features to predict the impact on project performance and provide recommendations for improvement, leading to suboptimal usage and varying performance outcomes.
Innovation Solution
A computing platform that utilizes data science and machine-learning models to analyze usage metrics of construction management software tools, generating predictions and insights to optimize performance on construction projects, including metric-, tool-, product-, and project-level analyses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If construction management software applications are used to manage construction projects, then project management capabilities are improved, but the ability to evaluate usage impact and predict performance is insufficient
Solution Approach 1:
The system performs preliminary actions by collecting and storing usage data throughout the construction project lifecycle. Usage metrics are continuously gathered and stored in a database before performance evaluation is needed, enabling later predictive analysis without interrupting ongoing project management activities.
Solution Approach 2:
The system implements feedback mechanisms by analyzing usage data and generating performance predictions that are fed back to users. The machine learning models process usage metrics and provide actionable insights about project performance, creating a closed-loop system where usage information leads to improved management decisions.
2Adaptability or versatility
If multiple software tools and features are utilized in construction management, then functional versatility is improved, but usage optimization and performance prediction become complex
Solution Approach 1:
The system segments the complex software ecosystem into distinct analyzable components. Each software tool and feature is tracked as a separate usage metric, allowing the system to analyze individual tool effectiveness while maintaining the ability to evaluate integrated workflows across multiple tools.
Solution Approach 2:
The system transforms complex usage patterns into standardized quantitative parameters. Usage metrics are converted into numerical values that can be processed by machine learning models, changing the complexity from qualitative software interaction analysis to quantitative parameter evaluation.
3Measurement precision
If usage data is collected and analyzed to predict performance, then performance prediction accuracy is improved, but data processing requirements increase
Solution Approach 1:
The system applies partial action by focusing data collection and analysis on the most impactful usage metrics. Rather than processing all possible software interactions equally, the system identifies and analyzes key usage patterns that have the greatest influence on project performance, reducing unnecessary data processing while maintaining prediction accuracy.
Data Source
AI summary
A computing system is configured to: (i) apply a machine-learning process to a training dataset to train a machine-learning model that is configured to (a) receive a first set of metric-level input values for a construction project of interest and a respective set of metric-level input values for each of a universe of reference construction projects, and (b) output a prediction of a party's performance on the construction project of interest and (ii) utilizing the machine-learning model to produce a prediction of a given party's performance on a given construction project of interest by inputting first and respective sets of metric-level input values into the machine-learning model and thereby causing the machine-learning model to (i) evaluate the sets of metric-level input values, and (ii) based on the evaluation of the sets of metric-level input values, output a prediction of the given party's performance on the given construction project of interest.