Scribd
Upload
18 views15 pages

Shubham Sirsat

The project titled 'Prediction of Building Cost' aims to develop a machine learning model that accurately estimates construction costs using historical data and modern technology. It addresses the challenges of traditional cost estimation methods by providing a user-friendly web interface for real-time predictions, which can aid in better project planning and budgeting. The project highlights the importance of accurate cost estimation for effective project management and explores future enhancements like 3D visualization and cloud-based features.

Uploaded by

228 - CM - Wagh Tejas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views15 pages

Shubham Sirsat

The project titled 'Prediction of Building Cost' aims to develop a machine learning model that accurately estimates construction costs using historical data and modern technology. It addresses the challenges of traditional cost estimation methods by providing a user-friendly web interface for real-time predictions, which can aid in better project planning and budgeting. The project highlights the importance of accurate cost estimation for effective project management and explores future enhancements like 3D visualization and cloud-based features.

Uploaded by

228 - CM - Wagh Tejas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 15

Final Report on

Project Title: Prediction of Building cost

Department of Computer Science and Engineering


Sanjivani University, Rural Education Society, Kopargaon, Maharashtra
2024-2025

Submitted by
Mr. Prashant Bandu Mundhe (2124UCEM2077)
Mr. Shubham Tukaram Sirsat (2124UCEM2090)
Mr. Tejas Raju Wagh (2124UCEM2013)
Mr. Yash Madhukar Patil (2124UCEM2091)
Mr. Omkar Popat Phopase (2124UCEM2019)
Mr. Pratik Suresh Deokar (2124UCEM2103)

Under the Guidance of:


Prof. Pravin Chokakkar
CERTIFICATE
This is to certify that, Project Entitled

Prediction of Building cost


Submitted by
Mr. Prashant Bandu Mundhe (2124UCEM2077)
Mr. Shubham Tukaram Sirsat (2124UCEM2090)
Mr. Tejas Raju Wagh (2124UCEM2013)
Mr. Yash Madhukar Patil (2124UCEM2091)
Mr. Omkar Popat Phopase (2124UCEM2019)
Mr. Pratik Suresh Deokar (2124UCEM2103)

Is submitted in the partial fulfillment of the prescribed syllabus of


SANJIVANI UNIVERSITY, Kopargaon of B.tech in computer
science and engineering.

Project Guide Head of Department


Prof. Pravin Chokakkar HoD. Mahendra Gawali
ACKNOWLEDGEMENT

We would like to express our heartfelt gratitude to our Project Guide,


Prof. Pravin Chokakkar, for his constant support, insightful
guidance, and invaluable encouragement throughout the course of our
project. His technical expertise, academic wisdom, and dedication to
mentoring have played a vital role in shaping the direction and quality
of our work. His timely advice, continuous follow-ups, and
constructive feedback greatly contributed to the successful completion
of this project.
We are also thankful to all the faculty members and staff who supported
and encouraged us during this project. Their guidance and motivation
were instrumental in our progress and learning throughout this journey.
ABSTRACT
Estimating the cost of building construction is an important step in
planning any construction project. A correct cost prediction helps
builders, engineers, and clients to plan their budget, manage resources,
and avoid unexpected expenses. In the past, cost estimation was mostly
done by experienced professionals using manual methods. However,
this process is often time-consuming and can sometimes lead to
mistakes. With the help of modern technology, we can now use data
and computer models to predict building costs more accurately. In this
project, we focus on using historical data from previous construction
projects to train a machine learning model that can estimate the cost of
a new building. The data includes various details such as total floor
area, number of rooms, type of materials, location of the building, labor
cost, and more. We use algorithms like Linear Regression or Decision
Tree, which analyze the data and learn patterns from it. Once trained,
the model can take inputs for a new project and provide an estimated
total cost. This makes the cost prediction process faster, more reliable,
and easy to use. This method is very useful for architects, contractors,
and real estate developers. It helps them to make better decisions, avoid
budget overruns, and improve project planning. It can also help clients
get an idea of how much their dream project will cost before starting.In
conclusion, predicting building cost using machine learning is a smart
solution that saves time and reduces errors. It brings better accuracy to
construction budgeting and helps all the people involved in a project to
work more efficiently and confidently.
CONTENTS
1. Introduction

2. Research

3. Problem statement

4. Requirements

5. Methodology

6. Flow Diagram

7. Screenshots

8. Impact on Society

9. Analysis

10. Future scope

11. Conclusion
1. Introduction
In the early phases of construction projects, limited design
information poses a challenge for accurate cost estimation. Proper cost
prediction is essential for investor decision-making, feasibility
analysis, and efficient planning. This project explores cost estimation
using modern tools and techniques such as Building Information
Modeling (BIM), which integrates geometry, materials, time, and
financial data. The goal is to provide a comprehensive, user-friendly
platform for predicting construction costs using reliable data and
machine learning models.

2. Problem Statement & Objectives


ProblemStatement:
Developing a website for cost estimation and prediction of residential
building construction.

Objectives:

1. Build an accurate and efficient model to predict construction


costs.
2. Collect and preprocess real-world construction data.
3. Design a user-friendly web interface for estimation.
4. Compare predicted and actual costs to validate accuracy.
5. Offer recommendations based on prediction outcomes.
3. Research Background
Research for the project is grounded in several academic studies:

1. Deep Learning with BIM (June 2023): Highlights challenges of


predicting costs during schematic design phases.

2. Extreme Learning Machine (Aug 2023): Compares machine


learning models for low-rise buildings, showing effectiveness of
ensemble methods

3. Support Vector Machine (SVM) (Nov 2021): Demonstrates


SVM’s 94.29% accuracy in predicting Indian construction costs

4. Requirements & Methodology


Hardware Requirements:

• Minimum: Intel i3, 4GB RAM, 256GB HDD


• Recommended: Intel i5/i7, 8GB RAM, 512GB SSD

Software Requirements:

• OS: Windows 10/11, macOS, or Linux


• Language: Python 3.x

.
5.Methodology:
The system is designed to forecast construction costs at early planning
stages using preprocessed historical data and machine learning
algorithms. A web-based UI enables users to input project parameters
and receive an instant estimate.
6. Flow Diagram & Features

Features include:
• Simple UI for user interaction
• Backend integration of cost prediction models
• Real-time estimation and recommendation generation
7. Screenshots
8. Impact on Society

8.1 Economic Benefits:


• Helps investors assess feasibility early
• Promotes job creation and revenue planning

8.2 Sustainable Development:


• Encourages responsible budgeting
• Facilitates eco-conscious planning

8.3 Social Impact:


• Makes project planning more inclusive
• Supports cost-efficient public infrastructure planning
9. Analysis & Future Scope

Analysis:
The platform provides fast, reliable cost predictions. It is easy to use,
saves time, and aids budgeting. Ideal for both individual and
professional users.

10. Future Scope:


• 3D visualization integration
• Advanced BIM features
• Cloud-based deployment
• Real-time data sharing and collaboration tools
• Connection to existing cost estimation software
11. Conclusion

Accurate construction cost estimation is crucial for effective


project management. This project developed a predictive system
that aids in early cost forecasting, potentially reducing financial
risks and enabling better planning. The integration of machine
learning and web technologies makes it a scalable and impactful
solution for modern construction needs.
12.Referance

• https://www.researchgate.net/publication/354261973_COST_ESTIMATI
ON_PERFORMANCE_IN_THE_CONSTRUCTION_PROJECTS_A_S
YSTEMATIC_REVIEW_AND_FUTURE_DIRECTIONS
• https://journalmodernpm.com/manuscript/index.php/jmpm/article/downlo
ad/576/502
• https://www.irjet.net/archives/V11/i9/IRJET-V11I9107.pdf

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy