Timing is one of the most common problems in construction work. Architects and design professionals create drawings and conceptual designs using data from the present to build structures in the future. Delays happen. Projects get dragged out because of approvals, permitting, weather and other unforeseen circumstances, further diminishing the relevance of the original design data. The interval between design and construction makes projecting costs incredibly difficult. Until recently, these cost forecasts have been guesswork at best.
Traditional forecasting data, developed during a time of far less computing power and data than is currently available, does not meet today’s standards for accurate planning and budgeting. These older methods simply do not predict market swings or sharp cost escalations well. But advances in technology have resulted in a new, useful tool for architects, engineers and other design professionals: predictive data.
By using predictive data, design professionals can consider all future factors at play in a region, including local labor rates and material costs. This makes it much easier to complete a project within the planned budget, even when the timeframe shifts.
Let’s dig in to how predictive cost data is an improvement on traditional forecasts. Fair warning: This is going to get a little math-heavy. You might want to put on a pot of coffee.
Predictive Costs: Macroeconomics and Data Mining Make the Difference
Although based on econometric principles and modeling techniques, predictive cost data differs from traditional econometric forecasts in two ways. First, traditional forecasts are based on macroeconomic theory, even though analysis of those macroeconomic indicators demonstrate them to be statistically insignificant. Predictive cost models disregard theory altogether and are based exclusively on data-driven empirical evidence instead.
This empirical evidence is the result of extensive exploratory data analysis and pattern-seeking visualizations of historical cost data with economic and market indicators. This updated approach has been extensively researched and validated by Dr. Edward Leamer, Professor of Global Economics and Management at UCLA. Only economic indicators that have “proven themselves” in exploratory analysis become candidates for model development, testing, validation and predictive cost estimates.
Second, predictive cost data uses mining techniques and principles to improve traditional econometric modeling practices. Since the 1990s, this family of processes and analyses has evolved from a mix of classic statistical principles, more contemporary computer science and machine learning methods. Data mining takes advantage of recent increases in computing power, data visualization techniques and statistical procedures in order to find patterns drivers of construction material and labor cost changes. Measures of these drivers and their relationships to each other and construction costs, along with their associated lead or lag times, are represented in an algorithm that predict future values for a defined material and location. This is a far more robust methodology.
Predictive Data and Design
What does all this—the econometric principles, empirical evidence and data mining—mean for design professionals? The ability to use predictive data that accounts for real market conditions (amount of construction versus labor availability) and commodity price impacts on material costs is critical to keeping designs in line with budgets. Predictive data makes the planning done today more realistic for tomorrow.
Construction professionals are already using predictive data to more accurately forecast the cost of construction up to three years before the project breaks ground. By using predictive data, project costs are not only forecasted accurately, but clients have more confidence in designs and the people who deliver them.