Gordian LogoPreconstruction planning has been, and continues to be, one of the most challenging aspects of the building lifecycle. Design professionals often must rely on yesterday’s data to plan tomorrow’s projects, but if they’re not including factors for present markets, historical data has proven to be unreliable. Further, historical data completely neglects to track trends that impact costs. But architects and other design professionals are expected to provide a project budget – and stick to it.

Thanks to modern data science and predictive analytics, those involved in the construction planning phases are now able to supplement historical data with reliable projections of future costs. Predictive cost data was developed by using a hybrid methodology that combines classical econometric techniques with contemporary data mining methodology to address the shortcomings of traditional forecast data.


The Problem

Until the economic crash of 2008, construction professionals relied on historic prices and localization factors to provide reasonably accurate costs to build. While these costs and factors are helpful when putting a budget together, stakeholders have increasingly voiced dissatisfaction with their accuracy (or lack of). Roughly 98 percent of construction projects go over budget.1 Furthermore, the market volatility and the shrinking construction labor pool have contributed to the inability to rely on past data to produce accurate budgets.

…market volatility and the shrinking construction labor pool have contributed to the inability to rely on past data to produce accurate budgets.

Prior to 2008, projects moved forward without major concerns about volatile costs. During and following the economic crash, a large number of subcontractors and smaller contractors were forced to leave the construction industry. When owners and builders were able to begin planning for regrowth, the construction labor force had been reduced by three-fifths.

Historic building costs and factors used in previous years became obsolete. More importantly, boards’ and investors’ concerns about the escalating costs grew exponentially. This led to a higher standard of accountability for construction and design professionals to manage and adhere to forecasted budgets. Bare material, labor and equipment rates account for 79 percent of total construction costs on average.2 Consequently, there is a clear and evident need for diligent management of construction material and labor costs.

When using current data at the capital planning stage-typically six to 24 months before construction starts-it becomes impossible to maintain an accurate estimate by the time the project breaks ground. Throughout the planning phase and all the way through construction, there are numerous unknowns that could cause unforeseen cost increases. Material prices can fluctuate greatly year-over-year based on interactions of various commodities and construction volume. Without a reliable method to keep track of all the moving parts, blown budgets, broken processes and finger pointing ensues. This can not only slow a project greatly; it can grind it to a halt.


The New Solution

Traditional forecasting data, developed during a time of far less computing power and limited availability of “big data,” simply does not meet today’s needs for accurate planning and budgeting. Traditional economic forecast methods do not predict market swings or sharp cost escalations well. Although based on econometric principles and modeling techniques, predictive cost data differs from traditional econometric forecasts in two ways.

Wood Material PriceFirst, traditional forecasts are based on macroeconomic theory, even when analysis of historical values of those macroeconomic indicators demonstrate them to be statistically insignificant predictors. 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 approach, clearly an update to the centuries-old theory-driven process, has been extensively researched and validated by Dr. Edward Leamer, Professor of Global Economics and Management at UCLA.3 Only economic indicators that have “proven themselves” in exploratory analysis become candidates for model development, testing, validation and resulting predictive cost estimates.

Second, predictive cost data uses mining techniques and principles to improve traditional econometric modeling practices. This family of processes and analyses has evolved since the 1990s from a mix of classic statistical principles and more contemporary computer science and machine learning methods.

Data mining methodology is specifically designed to analyze observational data instead of experimental data. A robust methodology, data mining takes advantage of recent increases in computing power, data visualization techniques and updated statistic procedures in order to find patterns and determine drivers of construction material and labor cost changes. Measures of these drivers and their relationships to each other and to construction costs, along with their associated lead or lag times, are represented in a statistical algorithm that predict future values for a defined material and location.


Predictive Data and the Future of Preconstruction

Quality predictive models are constantly monitored for degeneration, which is to be expected as economic and market conditions change. Decisions can be made as to whether a model needs to be refit or rebuilt based upon quarterly updates of external economic, construction-specific and market condition indicator data. In addition, special analyses and model checking can be performed as changes in market conditions are announced, such as tariffs imposed on steel and aluminum.

Where traditional economic forecasting techniques are simply unable to predict cost volatility and sudden market changes, predictive cost data provides a more robust and accurate data-driven alternative.

Predictive cost data has been used to more accurately predict the cost of construction up to three years before the project breaks ground.

One of the big challenges for design teams is creating a budget that is realistic and applicable to current and future stages of a project. On the other hand, construction teams often struggle to manage a budget presented by architecture or contractor teams. By using predictive data, preconstruction professionals can create budgets that consider all of the factors at play in a region, including local labor rates and material costs. This makes it much easier to complete a project on-time and within the planned budget.

Predictive cost data has been used to more accurately predict the cost of construction up to three years before the project breaks ground. The ability to have predictive data that accounts for real market conditions (amount of construction versus labor availability) and commodity price impacts on material prices is a critical insight in managing the budget from the design through construction. This also gives design professionals the power to instill confidence of their clients in their work. By using predictive data, projects are not only forecasted accurately, they are confidently approved and come to fruition sooner.

Take for example a fast food restaurant that plans to open 100 new stores over the next five years. Each store will be in a different location, and in time the costs of materials and labor will rise and fall in different markets. Predictive data does more than give an estimate of the total cost or even scaling cost over time, it allows you to optimize the build schedule and determine when and where the next restaurant should be erected.


Looking Forward

Conceptual square foot models are typically used in the capital planning phase and fall within 20 percent of actual costs. But when applying a true predictive multivariable database to these square foot models, thorough back-testing resulted in cost deviations of less than three percent up to three years in advance. This means owners, architects, engineers and other construction professionals can confidently predict future costs by applying a predictive cost dataset to conceptual construction square foot models.

Applying the same predictive data and proprietary algorithm to client-specific models and facilities results in highly accurate budgetary estimates at the capital planning stage. This accuracy allows construction projects to be completed within the estimated budget. Ultimately, the core value of using accurate predictive cost is the unprecedented ability afforded to construction professionals to understand future costs of projects.

 

Sources

1. “98 Percent of Construction Projects Go Over Budget. These Robots Could Fix That”, Digital Trends, Luke Dormehl, Jan. 26, 2018.

2 Calculated from historical RSMeans data.

3. Macroeconomic Patterns and Stories, Edward E. Leamer, Springer-Verlag, 2009.