Machine Learning in Construction. Predicting the Time and Cost of Projects . 📚 9 Lessons

Applying Machine Learning and Artificial intelligence to Construction. Price and Time Forecasting

Enrolment validity: 0 day

270.00 79.00

Description

In this course, we will step by step, using the example of real data, we will go through the main processes related to the topic “Big data and machine learning”.

🎓 In this fifth part:

✔️ We will examine in detail the basic types, terms and algorithms of machine learning. We go through the basic concepts of machine learning that beginners need. We will consider in more detail such algorithms as K-means supervised Machine Learning, Linear Regression and other algorithms for Machine Learning.

✔️ In practical lessons we will predict the time and cost of construction for the new project X, based on the data that we collected on previous projects. And in another lesson we will predict the cost of building project X and construction time by the parameters that we will set for the new project x

✔️ Then we take open source data for the San Francisco city. We will clear this raw data and display the data in the form of a charts and maps. We will collect various interesting insights from this public information. Then we will prepare the data to create a machine learning model and try to predict some parameters from this data.

📚 You will be guided through the basics of using:

  • Machine Learning Algorithms
  • Jupyter Notebooks for Data Science
  • K-means Machine Learning algorithm
  • Machine Learning Modeling Cycle
  • Linear Regression
  • Build a Predictive Model


🔎 Topics covered in this course:

📝 Lecture 2. What is machine learning? Key ML Terminology.
  • What is machine learning?
  • Key ML Terminology
  • Supervised Machine Learning
  • Unsupervised Machine Learning
  • Reinforcement Learning

📝 Lecture 3. Practice. Predict the price of houses. Dataset 1. Beginner’s Guide to Jupyter
  • Jupyter Notebooks for Data Science
  • Introduction to Kaggle for Beginners in Machine Learning
  • Supervised learning: predicting an output
  • Predict the price of a house

📝 Lecture 4. How does machine learning work? Prediction of construction time and cost.
  • Prediction of time and cost for small training dataset
  • K-means supervised Machine Learning algorithm
  • Understanding K-means Clustering in Machine Learning
  • Overview of Machine Learning Algorithms
📝 Lecture 5. Practice. Prediction of price and time. Data upload and preparation (Part 1/2)
  • Getting started with Machine Learning in MS Excel
  • A Kaggle Walkthrough – Cleaning Data
  • Beginner’s Guide to Jupyter Notebooks
  • Train, Validation Sets in Machine Learning
  • Splitting data into Training & Validation
📝 Lecture 6. Practice. Prediction of price and time. Evaluation Metrics (Part 2/2)
  • Determined the cost and time of construction work for project X
  • Evaluation Metrics for Machine Learning Model
  • Linear Regression for Machine Learning
  • How our algorithm works visually
  • Creating and Visualizing Decision Trees
📝 Lecture 7. Workflow of a Machine Learning project. Stages of the Machine Learning Modeling
  • Stages of the Machine Learning Modeling Cycle
  • Learning Phase of Machine Learning
  • Inference from Model
  • Machine Learning Deployment Pipeline
📝 Lecture 8. Practice. Data loading and preparation to Analyzing (Part 1/2).
  • Build a Predictive Model
  • Training and Validation Sets: Splitting Data
  • Determining the “estimated cost” by parameters
  • Predict the “estimated cost” for arbitrary parameters
  • Evaluation Metrics for Machine Learning Model
  • Linear regression Predictive Models
📝 Lecture 9. Practice. Cost Prediction. Way to build a Predictive Model (Part 2/2).
  • Find Open Datasets
  • Loading large Datasets into Kaggle
  • Data visualization and analysis in Kaggle
  • Average postcode price on a San Francisco map
  • Total cost of all building permits for the postal code
  • Average “estimated cost” by type of housing

What Will I Learn?

  • What is machine learning?
  • Key ML Terminology
  • Supervised Machine Learning
  • Unsupervised Machine Learning
  • Reinforcement Learning
  • Jupyter Notebooks for Data Science
  • Introduction to Kaggle for Beginners in Machine Learning
  • Supervised learning: predicting an output
  • Predict the price of a house
  • Prediction of time and cost for small training dataset
  • K-means supervised Machine Learning algorithm
  • Understanding K-means Clustering in Machine Learning
  • Overview of Machine Learning Algorithms
  • Getting started with Machine Learning in MS Excel
  • A Kaggle Walkthrough – Cleaning Data
  • Beginner's Guide to Jupyter Notebooks
  • Train, Validation Sets in Machine Learning
  • Splitting data into Training & Validation
  • Determined the cost and time of construction work for project X
  • Evaluation Metrics for Machine Learning Model
  • Linear Regression for Machine Learning
  • How our algorithm works visually
  • Creating and Visualizing Decision Trees
  • Stages of the Machine Learning Modeling Cycle
  • Learning Phase of Machine Learning
  • Inference from Model
  • Machine Learning Deployment Pipeline
  • Find Open Datasets
  • Loading large Datasets into Kaggle
  • Data visualization and analysis in Kaggle
  • Average postcode price on a San Francisco map
  • Total cost of all building permits for the postal code
  • Average "estimated cost" by type of housing
  • Build a Predictive Model
  • Training and Validation Sets: Splitting Data
  • Determining the "estimated cost" by parameters
  • Predict the "estimated cost" for arbitrary parameters
  • Evaluation Metrics for Machine Learning Model
  • Linear regression Predictive Models

Topics for this course

9 Lessons01h 24m

Introduction to the Course

Machine Learning. An Introduction.

Practice. How does machine learning work?

Workflow of a Machine Learning project.

Practice. San Francisco – explore Building Permits Data. Build Predictive Model.

Share

Course Details

  • Level: All Levels
  • Categories: Big DataMachine Learning
  • Total Hour: 01h 24m
  • Total Lessons: 9
  • Last Update: September 30, 2021

Requirements

  • You need only the installed Windows System
  • You do not need any special programming knowledge or theoretical knowledge of Python

Target Audience

  • Beginners who are interested in Big Data and Machine Learning using Python
  • This course can be opted by anyone (students, developer, manager) who is interested to learn big data
  • Professionals in the construction and AEC industry
Share