Data Analysis Environment
A centralized data analysis environment offers significant time savings, improved analysis quality and trust, and a common platform around which to standardize reporting, visualization, and analysis tool, techniques, and practices.
Populate this environment with authoritative, curated datasets and develop standardized data transformations needed to support routine TAM data analysis needs. Provide standardized capabilities and solutions to address ad-hoc analysis requirements (for example, use of a data lake to temporarily expose data for time-bound data exploration activities).
TAM Data Visualization Practices
Standardized data reports and visualizations are effective communication and information sharing tools. Common visualization techniques include:
- Straight Line Diagraming Tools: Simplify the representation of the roadway in order to provide location referencing context.
- Performance Dashboards: Track and represent agency goals, objectives, and performance measures to guide daily asset management work activities and decisions.
- Data Marts and Interactive Reporting Tools: Provide highly usable, ad-hoc reporting functions.
TAM Data Analysis Practices
Many DOTs are developing specialized data analysis and data science programs to support TAM and other business areas. Analytical techniques commonly leveraged to support TAM include are provided in the conceptual examples.
The following terms are used within this Section.
Data that is too large and complex to be dealt with through traditional data processing applications and methods.
Systems, applications, and process that change raw data into useful business information.
A scaled down version of a data warehouse, meeting a particular analytical, reporting, or decision-support need.
The use of scientific methods, processes, algorithms, and systems to extract knowledge and insights from structured and unstructured data.
Use geospatial information to integrate and compile disparate datasets useful for TAM analysis.
Data, Text, and Process MiningProvide techniques to identify anomalies, patterns, and correlations within the large datasets available to TAM practitioners.
Temporal AnalysisEnable examination or modeling of a variable within a data set over time, useful for applications such as asset deterioration modeling, performance trend analysis, investment scenario analysis, and asset work history or use evaluation.
Trade-Off AnalysisFacilitate the comparison of investment priorities with fiscal constraints (both within a given asset program, or across multiple programs).
Prescriptive AnalyticsUse business analytics to find the best course of action for a given situation (e.g. selecting a TAM treatment for a specific location or asset).
Predictive ModelingApply business analytics to forecast future conditions (e.g. asset condition forecasting).
Predictive AnalyticsUse data mining, statistics, modeling, machine learning, artificial intelligence, or other techniques to make predictions about unknown future events. These techniques are emerging in DOT practice.
Decision ScienceScore projects and optimize of selection for programming based on benefits, costs, and other measures to assign relative importance. Seen in multi-objective project prioritization and decision-analysis applications.