Your learning journey starts here – select a chapter group
Part nine is dedicated to big data, machine learning and predictive analytics in the construction industry. It explores the transition from intuitive decision making to objective analysis based on historical data. Practical examples are used to demonstrate big data analysis in construction, from parsing the San Francisco building permit dataset to processing CAD -projects with mil-lions of elements. Special attention is given to machine learning methods for predicting the cost and schedule of construction projects, with a detailed discussion of linear regression and k-nearest neighbor algorithms. It is shown how structured data become the basis for predictive models to as-sess risks, optimize resources and improve project management efficiency. The part also provides recommendations on how to select representative data samples and explains why large data sets are not always required for effective analysis.
146 Big data in construction from intuition to predictability
The term “big data” does not have a strict definition. The concept originally appeared when the volume of information began to exceed the capabilities of traditional methods of its processing. Today, the volume and complexity...
147 Questioning the feasibility of big data correlation, statistics and data sampling
Traditionally, construction was based on subjective hypotheses and personal experience. Engineers assumed – with a certain degree of probability – how the material would behave, what loads the structure would withstand and how long the...
148 Big data analyzing data from San Francisco’s million building permit dataset
Working with open datasets provides a unique opportunity to put into practice the principles discussed in previous chapters: judicious feature selection, representative sampling, visualization, and critical analysis. In this chapter, we will explore how complex...
149 Example of big data based on CAD data (BIM)
In the following example we will analyze a large dataset using data from different CAD tools (BIM). To collect and create the large dataset, a specialized automated web crawler (script) was used, configured to automatically...
150 IoT Internet of Things and Smart Contracts
IoT The Internet of Things represents a new wave of digital transformation in which every device gets its own IP address and becomes part of a global network. IoT is a concept that involves connecting...
151 Machine learning and artificial intelligence will change the way we build
The databases of the various systems in the construction business – with their inevitably decaying and increasingly complex infrastructure – are becoming a breeding ground for future solutions. Company servers, like a forest, are rich...
152 From subjective assessment to statistical forecast
The era when strategic decisions depended on the intuition of individual managers (Fig. 9.2-4) is a thing of the past. In an increasingly competitive and challenging economic environment, a subjective approach is becoming too risky...
153 Titanic dataset Hello World in the world of analytics data and big data
One of the most famous examples of using ML in data analytics is the analysis of the Titanic dataset, which is often used to study the probability of survival of passengers. Studying this table is...
154 Machine learning in action from Titanic passengers to project management
The main hypothesis used to explore the machine learning framework based on the Titanic dataset is that certain groups of passengers had a higher chance of survival. The small table of Titanic passengers has become...
155 Predictions and forecasts based on historical data
The data collected on the company’s projects opens up the possibility of building models capable of predicting the cost and time characteristics of future, not yet realized objects – without time-consuming manual calculations and comparisons....
156 Key concepts of machine learning
Machine learning is not magic, it’s just math, data and finding patterns. It has no real intelligence, but is a program trained on data to recognize patterns and make decisions without constant human involvement. Machine...
157 An example of using machine learning to find project cost and schedule
Estimation of construction time and cost is one of the key processes in the activities of a construction company. Traditionally, such estimates are made by experts based on experience, reference books and regulatory databases. However,...
158 Project cost and time prediction using linear regression
Linear regression is a fundamental data analysis algorithm that predicts the value of a variable based on a linear relationship with one or more other variables. This model assumes that there is a direct linear...
159 Project cost and time predictions using the K-nearest neighbor algorithm (k-NN)
We use the k-Nearest Neighbors (k-NN) algorithm as an additional predictor to estimate the cost and duration of a new project. The K-Nearest Neighbors (k-NN) algorithm is a supervised machine learning (supervised machine learning) method...
160 Next steps from storage to analysis and forecasting
Modern approaches to working with data are beginning to change decision-making in the construction industry. Moving from intuitive assessments to objective data analysis not only improves accuracy, but also opens up new opportunities for process...
