0% found this document useful (0 votes)
23 views34 pages

Revised Data Gathering

Uploaded by

anggemaranan1208
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
23 views34 pages

Revised Data Gathering

Uploaded by

anggemaranan1208
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 34

CODRO: AI- POWERED MATERIAL COST ESTIMATION FOR CONSTRUCTION

MANAGEMENT

A Thesis Presented to the

Faculty of College of Engineering, Architecture, Technology and Sciences

John Paul College

CANDARI, ARJIE S.

EVANGELISTA, IVY P.

FALCUTILA, KRISTEL JOY G.

HELERA, LORENZ JAKE S.

MANGLO, PRECY V.

MARANAN, ANGELA

RIOJA, ANA L.

November 2024
TABLE OF CONTENTS

TITLE PAGE
ABSTRACT

CHAPTER 1
1 THE PROBLEM AND ITS SCOPE
i. Introduction ------------------------------------------------------------ 2
ii. Background of the Study ------------------------------------------- 3
iii. Objectives of the Study --------------------------------------------- 4
iv. Statement of the Problem ------------------------------------------ 5
v. Significance of the Study ------------------------------------------- 6
vi. Hypothesis of the Study -------------------------------------------- 7
vii. Scope and Delimitation --------------------------------------------- 8
viii. Theoretical and Conceptual Framework ----------------------- 10
ix. Definition of terms --------------------------------------------------- 12

CHAPTER ll
2 REVIEW OF RELATED LITERATURE AND STUDIES ----------------------- 14 - 18

CHAPTER III
3 METHODOLOGY ----------------------------------------------------------------------- 19 - 22
i. Research Design ------------------------------------------ 19
ii. Locale of the Study --------------------------------------- 20
iii. Respondents of the Study ------------------------------ 20
iv. Sampling Procedure --------------------------------------20
v. Data Gathering Procedure ------------------------------ 20
vi. Statistical Analysis ---------------------------------------- 20
vii. Ethical Considerations ----------------------------------- 21
viii. References ------------------------------------------------- 22
ABSTRACT

This thesis delves into the possibilities of integrating Artificial Intelligence (AI) into the

financial management processes of the construction sector, with a specific focus on enhancing

the accuracy and efficiency of cost estimation. By scrutinizing the shortcomings of conventional

financial management approaches in construction, such as proneness to human error, limited

real-time data analysis, and challenges in adapting to market dynamics, the research

underscores the need for AI intervention. Drawing insights from existing literature on AI's role in

financial management, the thesis proposes a structured framework for integrating AI-powered

solutions to mitigate these challenges effectively.

The study delves into how AI technologies like machine learning and deep learning can

leverage historical project data to recognize patterns and generate precise cost estimates.

Additionally, the research explores AI's potential benefits in risk evaluation, resource allocation,

and financial forecasting, with the ultimate goal of bolstering the financial robustness and

profitability of construction ventures. The outcomes of this study add to the evolving

understanding of AI's transformative capabilities in the construction domain, offering practical

insights for industry practitioners and scholars keen on optimizing financial management

practices through innovative tech-driven approaches.

1
INTRODUCTION

Estimating the construction costs is one of the crucial component in managing the

project in the construction industry. It affects the choices about the financial budgeting, resource

allocation, and project viability. In the past, reviewing material lists, examining the market price,

and computing quantities and costs have all been part of the human cost estimation. This kind of

method is laborious, prone to human mistake, and necessitates a high level of skill. However,

artificial intelligence(AI) offers chances to enhance and expedite cost estimation as the

construction sector moves toward digital solutions.

According to Singh et al., 2022, Artificial intelligence accuracy is further improved by its

flexibility in responding to shifting market conditions. Geographical location and time have an

impact on material prices, and artificial intelligence can incorporate real-time pricing information

nearby resources. This makes it possible for AI-based systems automatically modify cost

estimates in response to local price patterns, guaranteeing that estimates accurately represent

the state of the market. Thus, it made available to stakeholders because it is more precise and

contextually relevant cost forecasts that improved the financial planning and decision-making.

In addition, construction sector can gain long-term advantages from the use of AI Into

cost estimation. Artificial Intelligence helps reduce human error by decreasing the need for

manual calculation, and it gives construction managers more accurate data for budgeting.

Furthermore, when artificial intelligence tools process more data, they can learn and become

more accurate over time, generating cost predictions that more accurate. As a result of this

cycle of continual improvement, artificial intelligence is a future- proof solution for the always

2
changing construction landscape since it can adjust to new materials, cost databases, and

industry norms.

Moreover, this study aims to create an AI-based system that can automatically calculate

the project cost by taking pictures of construction material lists. In order to improve the

effectiveness and dependability of cost estimating, the suggested study makes use of picture

recognition, data processing and database integration. Because it offers a contemporary

alternative to the traditional approaches to cost estimation, this study is noteworthy. To illustrate

the benefits of artificial intelligence in terms of accuracy, efficiency and speed, the study will

compare the AI-based system with the traditional excel spreadsheet methods.

3
BACKGROUND OF THE STUDY

The construction and infrastructure sector plays a significant role in leading the global

economy, especially on providing jobs and advancing technology. However, it can’t deny that it

continues to face numerous challenges, like excessive costs and project delays. Proper

management of materials is important to efficiently control expenses and time, yet traditional

methods, which usually base on manual calculations, may lead to some errors and higher risks

in the project.

In construction management, accurate cost estimation is important to finish the project

successfully. Traditional cost estimation methods have been used for a long time, depending on

manual calculations, historical data, and the knowledge of engineers and estimators.Throughout

these types of ways, estimates experience a review of construction drawings, specifications,

and materials in order to accurately determine costs, commonly using cost databases or

construction cost guides to consider price changes and market shifts.

While these methods are important in the industry, being able to take a lot of time and

depend largely on the estimator's ability and decision-makingin order to make sure an accurate

projections. It is undeniable that the usage of traditional methods can leads to errors, especially

when sudden issues happen during a project. Studies imply that traditional methods can have

accuracy rates as low as 60-70%, leading to increased risks of rework, delays, and cost

overruns (Hwang & Ng, 2013). Additionally, manual estimation is time-consuming, often taking

significantly longer to complete, especially for large projects, further complicating project

management and budgeting.

Building Information Modeling (BIM) proved to be a more advanced alternative to

overcome all these limitations. This automated material take-off will provide much higher
4
accuracy and speed than in estimations compared with tradition or manual cost estimation.

Despite the high initial costs of implementing BIM, including the development of software,

training, and model creation, it greatly contributes to overall cost savings. This is due to the

reduction of material waste and more effective project management." Research shows that BIM

can increase accuracy to 85-90% by reducing human error and providing consistent data

throughout the project's lifecycle (Bryde et al., 2013). BIM also enhances efficiency, reducing

estimation time by 50-70%, and offers real-time updates as project designs change (Azhar,

2011).

It helps out with material estimation by using artificial intelligence to introduce a

cuttingedge approach towards cost estimation in a fully innovative manner. Compared with the

traditional and BIM for cost estimation, AI-powered material cost estimation uses advanced

image recognition and AI technology to streamline the calculation of material costs. This method

AI-powered material cost estimation employs advanced image recognition and AI technology to

simplify the calculation of material costs. By capturing a simple image of written materials as

well as their quantities, comparing it with traditional methods and BIM, the AI system rapidly

processes the image to draw out essential information just like material names, quantities, and

units. It then matches this data with current pricing to instantly calculate the total cost. This

method takes the need for manual calculations, saving time and minimizing errors or mistakes.

Eventually, this AI-driven cost estimation offers a faster, more accurate, and more efficient way

to estimate material costs, enhancing both project planning and decision-making. AI can notably

enhance the material estimation process, making it faster, more accurate, and more accessible,

especially for smaller projects or specific material lists.

5
OBJECTIVES OF THE STUDY

General Objectives:

This research aims to create an artificial intelligence system that calculate construction

project costs by examining photos of item lists, improving the accuracy, efficiency and timeline

of cost estimation procedures.

Specific Objectives:

The research is proposed to:

(1) To create and hone an artificial intelligence model that can identify and extract

information from picture lists of construction material lists

(2) To develop an algorithm using the gathered data to estimate the construction costs of a

project.

(3) To assess how accuracy and efficient the artificial intelligence system is in contrast to

Excel-based cost estimation.

(4) To identify possible challenges and restrictions when utilizing artificial intelligence to

automate the calculation of construction costs.

(5) To evaluate the artificial intelligence tool’s applicability and reliability in actual

construction project scenarios.

6
STATEMENT OF THE PROBLEM

This study seeks to address the following questions regarding the integration of AI into

material cost estimation in construction projects:

1.) What are the limitations of traditional material cost estimation methods?

•Reliance on Excel spreadsheets

• Inefficiency and time consumption

•Monotony in the process

•High percentage of human error

2.) How do traditional methods affect construction project outcomes?

•Inaccurate cost predictions

•Budget overruns

•Delays in project timelines

•Financial setbacks as projects grow in complexity

3•How can AI improve the material cost estimation process?

•Reduction in human error

•Streamlined and automated estimation practices

•Enhanced accuracy in cost predictions

•Increased efficiency and time savings

4.) What benefits does AI offer for the future of construction material estimation?

•A more reliable framework for cost assessment

•Improved project outcomes with fewer delays

•Better resource allocation and budget management

7
SIGNIFICANCE OF THE STUDY

The study "CODRO: AI- Powered Material Cost Estimation for Construction

Management” holds significance in enhancing construction industry efficiency It is beneficial for

a wide range of stakeholders in the construction industry:

Project Managers and Contractors. They will benefit because an artificial

intelligencebased solution reduces the amount of time spent on manual data entry, allowing

managers to focus on higher level planning and strategic decisions. Faster and more accurate

cost estimation will help them with project budgeting and effective resource allocation.

Estimators and Quantity Surveyors They are the professionals who rely on precise

cost estimates to inform their decisions about project viability and budgeting. This artificial

intelligence tool can be a useful tool, allowing estimates to verify calculations and reduce errors.

Clients and Investors. For clients and investors, precise cost estimation is crucial for

risk assessment and financial planning. This study’s artificial intelligence system can enhance

budget projections. Promoting increased transparency and confidence in project proposals.

Researchers and Technologists. The results of the study will be useful to researchers

looking into artificial intelligence applications in cost estimation or in construction industry. It

looks how artificial intelligence is actually used in construction management, which could have

an effect on future studies in construction automation.

By conducting this study, stakeholders such as project managers and contractors,

estimators and quantity surveyors, clients and investors, and researchers and technologists will

8
benefit from the valuable insights and recommendations. Ultimately, the study addresses the

potential to enhance efficiency, accuracy, and set a new standard in the construction industry for

accurate, automated cost estimation.

9
HYPOTHESIS OF THE STUDY

The researcher's objective in this study is to test the following hypothesis about

the data's results:

Null Hypothesis: there are little to no significant differences in the means of the

eigenvalues between traditional method of material cost estimation and CODRO AI

integrated method for material cost estimation

Alternative Hypothesis: There are significant differences in the means of the

eigenvalues between traditional method of material cost estimation and CODRO AI

integrated method for material cost estimation

10
SCOPE AND DELIMITATION

This thesis will investigate the potential of Artificial Intelligence (AI) in enhancing material

cost estimation within the context of Oriental Mindoro. The scope is defined by the following

parameters:

1. Focus Area:

- Material Cost Estimation: The thesis will focus exclusively on the material

component of financial management, excluding labor, overhead, and other project costs. This

will allow for a deep dive into the complexities of material cost prediction.

2. Geographical Scope:

- Oriental Mindoro: The research will be confined to the province of Oriental

Mindoro, ensuring the data collected and the AI models developed are relevant and specific to

the local market and construction industry.

3.Data Collection:

- Oriental Mindoro-specific Data: All data related to material costs will be sourced

from within Oriental Mindoro. This includes, but is not limited to: Local market prices for

construction materials

- Historical material cost data from past projects - Supply chain dynamics and

material availability in the region - Local regulations and policies affecting material costs

4.AI Application:

11
- AI Models for Material Cost Estimation: The thesis will explore the application of

a wellknown AI techniques: Machine Learning (ML) algorithms for predicting material costs

based on historical data and other relevant factors.

5. Evaluation and Validation:

- Real-world Application: The effectiveness of the developed AI models will be

evaluated through real-world case studies within Oriental Mindoro. This will involve comparing

AI-generated cost estimates with actual project costs and assessing the accuracy and

efficiency of the AI-based approach.

6. Potential Benefits:

- Improved Cost Accuracy: The thesis aims to demonstrate how AI can contribute

to more accurate and reliable material cost estimations, reducing project overruns and

improving financial planning.

- Enhanced Efficiency: AI-powered tools can streamline the material cost

estimation process, saving time and resources for construction professionals. - Data-driven

Insights: The analysis of material cost data using AI can provide valuable insights into market

trends, material availability, and cost drivers, aiding in informed decision-making.

7. Limitations:

- Data Availability: The availability and quality of data within Oriental Mindoro will

be a crucial factor in the success of the research.

- Generalizability: The AI models developed may not be directly transferable to

other regions due to variations in market dynamics and construction practices. This clearly

defined scope will guide the research and ensure the thesis delivers a valuable contribution to

12
the field of AI-assisted material cost estimation, specifically within the context of Oriental

Mindoro.

CONCEPTUAL FRAMEWORK

13
FEEDBACK

Figure 1-1. Conceptual Framework

The researcher used these three sources or stimuli for creating conceptual framework:

INPUT -PROCESS -OUTPUT. In the evolving landscape of project management and technology

integration, the relationship between materials cost estimation and the deployment of artificial

intelligence (AI) has garnered significant attention. This conceptual framework outlines the

interplay between these elements, emphasizing the integration of AI for material cost

management and efficient material cost.

At the core of this framework lies the input variable: artificial intelligence. AI

encompasses the application of algorithms and machine learning techniques designed to

automate processes, enhance decision-making, and improve efficiency across various fields. As

organizations increasingly rely on AI to drive innovation and optimize operations, understanding

the factors that contribute to its effectiveness becomes paramount.

14
The process variable involves the collection and analysis of material cost through social

hardware stores and testing through repeated trial- and -error methods to improve accuracy and

reliability.

The output variable is the achievement of efficient material cost management, which

refers to the process of predicting the costs associated with the materials required for a project.

This estimation is critical for effective budgeting and resource allocation, impacting not only

financial planning but also the overall success of projects. Accurate materials cost estimation is

essential for minimizing waste, avoiding budget overruns, and ensuring that resources are

deployed

efficiently

DEFINITION OF TERMS

15
Artificial Intelligence

- refers to the use of advanced algorithms and machine learning techniques to analyze

historical project data, design plans, materials, labor costs, and factors to predict and

optimize the overall costs of a construction project.

Automation

- The process of using technology to handle routine tasks with minimal human involvement,

enhancing efficiency and accuracy.

Building Information Modeling (BIM)

- in construction estimation for construction management is the process of using a digital

3D model to generate detailed design, material quantities, and cost data, enabling more

accurate, real-time, and collaborative project cost forecasting and management.

CODRO

- Captured Observations through Document Review and Outlay Estimation

Construction Management

- involves planning, budgeting, coordinating, and supervising construction projects from

the start to finish.

Cost Capture

- a process of gathering data cost through capturing in real time

Data Accuracy

16
- the precision and reliability of data used in material cost estimation.

Efficiency

- the overall productivity and accuracy achieved in the cost estimation process.

Spreadsheet Excel

- is a software used to store, manipulate and analyze data.

Material Cost estimation

- in construction management involves determining the total cost of materials required for a

project by calculating quantities, sourcing unit costs.

Risk Management

- the process of guiding a construction project from the start to finish by planning,

coordinating and managing various tasks.

Time Efficiency

- the speed in AI powered reduce the time needed for estimation compared to traditional

methods.

Traditional methods

- involves manual calculations based on detailed quantity takeoffs from blueprints, historical

data, and unit price.

CHAPTER 2

17
REVIEW OF RELATED LITERATURE AND STUDIES

This study discusses various research papers that were examined in order to accomplish

the study goal. The traditional way of financial management has been regarded as the

commonly used method regarding material cost estimation in today’s construction industry. This

study touch upon disadvantages of the current financial management method and how it can be

improved with the help of modern software’s.

RELATED LITERATURE

Effectiveness of material cost estimating has an important factor in the construction

project management, as it develops the timelines for a project and statement of budget and it

financial outcomes. Construction cost estimating process based on manual calculation

procedures in terms of traditional method using historical data and expertise. It often caused

mistakes and delays. The advancement of Artificial Intelligence has transformed this process to

achieve more accurate, efficient, and dynamic approaches for estimating costs for materials. In

progress of AI enhanced estimations of material costs by the analysis of large datasets, complex

pattern recognition, and generation of more precise forecasts of cost. Construction cost

estimating process based on manual calculation procedures in terms of traditional method using

historical data and expertise.

In progress of AI enhanced estimations of material costs by the analysis of large

datasets, complex pattern recognition, and generation of more precise forecasts of cost

according to Pan and Zhang (2021), AI-based models are designed to automate the estimation

procedure, with more reliable predictions through learning from historical project data.

18
The use of AI is to automate this traditionally manual and time consuming task brings

with it big advantage in terms of efficiency, reduce errors, and better decision making. Additional

progress or development in AI may be able to modernize construction processes even more and

contribute to innovation in the industry.

Regression models, basis of controlled machine learning, have proven to be a useful tool

in the construction industry. By evaluating historical project data, these models can accurately

predict material costs based on factors such as material type, quantity, location, and

specifications. As Becerik-Gerber et al. (2012) highlight, this application of regression models

has the potential to optimize resource allocation, enhance cost control, and improve overall

project profitability.

Now (Zhou et al., 2021) highlighted, apart from time and accuracy, AI tools give

costoptimization benefits. There is a feature called scenario analysis of an AI model, which tries,

in real-time, multiple cost-saving strategies based on choices of different materials, supplier

conditions, and logistical factors. Therefore, construction managers are authorized to make

more informed choices. A construction manager can make choices about the most need

materials and suppliers for a project with great decision.

While AI-powered solutions keep promise for revolutionizing the construction

industry, their success stays on the availability of high-quality, complete datasets. As Akinci et

al. (2018) emphasize, the challenge of gathering clean and reliable historical data can greatly

limited the accuracy of AI-based models. This data deficiency often arises from various factors,

including inconsistent data formats, missing information, and a lack of standardized data

collection practices within the industry. To get the most out of the potential of AI, construction

19
firms must invest in more reliable data management strategies and work together to establish

industry-wide data standards.

The author (Xie et al., 2020) point out, a major challenge for small and medium-sized

construction firms in adopting AI technology is the significant upfront costs. High implementation

costs also act as a barrier to adopting the AI system for small and medium-sized firms during

the initial stages of its use. These technologies are typically expensive in terms of software,

hardware, and training employees, which may not be affordable for most construction

companies.

But in that case the initial costs related with the AI technology investment are

considerable, particularly for the small to medium sized firms. It often pays off in the end,

however, with improvements in availability and low cost, benefits like efficiency, better decisions,

and outcomes on projects result for these companies. Investing in the field of AI on a

construction firm would prove a competitive advantage over other constructions while lowering

operation costs, in order to achieve quality in which the construction will come.

The major critical issue in the Philippine construction industry is accurate material cost

estimation, wherein, without doubt, project cost overruns, delays, and material shortages are

also leading. The traditional methods of cost estimation use manual calculations, which are

prone on errors and consume much time. However, use of Artificial Intelligence for material cost

estimation in current construction projects with increasing complication and material cost means

very much to bring efficiency, accuracy, and cost control in itself. Current practices in the

Philippines, although still at its beginning, prove great interest in adoption with AI especially ML

and predictive analytics, to accurately and efficiently improve material cost estimation.

20
One of the early studies conducted within the Philippine context by the author Salazar et

al. (2020) The study addressed the potential of using AI techniques in estimating labor and

materials costs in construction projects. Their study ran machine learning algorithms on

historical project data that showed AI systems can significantly improve the accuracy of cost

predictions, mainly for medium to large projects in urban areas like Metro Manila. Much faster

and more reliable estimates open that a much larger scope of stakeholders having ability to

facilitate decisionmaking. So this is one of the trends globally as AI tools, particularly neural

networks and BIM (Building Information Modeling), are used to automate material cost

estimation and present updates in real time based on changes in project variables.

Highly significant advantages can be found with AI in material cost estimation in the

Philippine construction sector. These include the potential for improved accuracy and thus better

cost optimization, as well as time efficiency. According to Panganiban and Del Mundo (2019)

the ability of AI to avoid mistakes and biases natural in traditional forms of cost estimations. AI

might, for example use machine learning algorithms for processes not limited to simply past

data input from projects but include ups and downs prices of materials, concerns in supply, and

regional issues all to improve assessing the reliability of it. Their study also laid down the fact

that AI can optimize material choices; it opens avenues for project managers to calculate and

choose the most cost-effective materials for a particular job, thus minimizing wastage and

improving budget control.

As noted by Santos et al. (2020) while in most cases, construction firms located in rural

areas or outside of Metro Manila cannot gain access to structured data for estimating the

material cost. AI models, though can interact and learn from various datasets, such as regional

market trends and historical project data, thereby improving the process of cost estimation even

21
in areas with relatively limited data availability. From such data, AI can make more precise

material cost estimates, especially for projects in underserved locations where traditional data

are scarce.

However, the adoption of AI in the construction industry in the Philippines has its own

challenges. Primarily, the quality and availability of data. Many construction firms in the

Philippines rely on old methods of estimating costs and ain’t got a focused database of

information on construction. This spread information, combined with keeping records

differences, goes the cost estimates produced by AI models unreliable. In fact, Lauzon and Dela

Cruz (2021) stated that the gaps in the data are still one of the biggest concerns when it comes

to implementing AI in construction management. The challenge here would be that Philippine

construction industries lack structured, accurate, and comprehensive datasets upon which the

effective operation of AI models relies.

In terms of sustainability, AI’s role in material cost estimation is also expected to grow,

especially in helping construction firms closer to environmentally friendly and cost-efficient

materials. AI models can adopt the life-cycle costs and environmental impact of materials,

allowing for more sustainable choices in construction projects. PICE (2021) noted that as the

Philippine construction industry moves toward more green building initiatives, AI could help firms

meet sustainability goals while maintaining cost control. Furthermore, as AI technologies

become more affordable and accessible, it is likely that smaller construction firms will slowly

adopt these tools, leveling the playing field and allowing even small contractors to benefit from

AI’s capabilities.

22
RELATED STUDIES

Material cost estimation errors in construction can vary significantly based on region,

estimation method, and external factors such as market conditions and supply chain disruptions.

Below are the error percentage of material cost estimation insights based on various sources:

Traditional Estimation Methods (Manual/Excel-Based)

Errors in material cost estimation can range from 10% to 25%, primarily due to factors

like inaccurate market data, human error, and fluctuating prices of materials. Issues such as

supply chain disruptions and inconsistent pricing often lead to such discrepancies.

Technological Methods (AI and Software-Based):

Errors are usually reduced to 5% to 10% when using advanced software tools. However,

even with AI, inaccuracies can arise from poor input data or system configuration errors. Despite

these improvements, unpredictable events such as natural disasters or geopolitical factors can

still cause sudden spikes in material costs.

International (Developed Markets):


Traditional Methods:

In developed markets like the US and the UK, where more structured data and

sophisticated systems are often in place, errors in material cost estimation are generally lower,

typically around 5% to 15%. Despite better data systems, these countries still experience

fluctuations, particularly during global crises such as the COVID-19 pandemic, which disrupted

supply chains and caused material shortages.

23
Technological Methods:

The use of AI, BIM (Building Information Modeling), and cost estimation software

reduces the error margin to 3% to 8% in high-income countries. These tools help in adjusting

real-time data, forecasting material needs accurately, and incorporating market trends.

However, the global rise in material costs, especially in sectors like energy-intensive materials

(steel, cement), has impacted even these accurate methods.

In both the local and international engineering industries, various financial management

tools are employed to streamline cost tracking, budgeting, and overall project management.

These are the most used way/software in the industry.

Local Financial Management Tools:

1. Microsoft Excel: Frequently used in smaller firms for financial analysis and cost tracking,

though manual, due to its flexibility.

2. SAP ERP: Popular among large firms for managing finances, procurement, and

accounting within one integrated platform, widely used in large-scale projects.

3. Procore: A construction management software with financial management features,

facilitating easier cost tracking and budget management.

4. QuickBooks: Suitable for small to medium-sized businesses, offering tools for

accounting, expense tracking, and financial reporting.

International Financial Management Tools:

1. Primavera P6: Extensively used for project scheduling and management, with integrated

budgeting, cost control, and forecasting.

2. Oracle ERP Cloud: A comprehensive financial tool, ideal for large enterprises, managing

budgeting, project financials, and supply chain aspects.

24
3. CostOS: Specialized in cost estimation and project cost control, particularly for large

engineering projects.

4. Sage 300 Construction and Real Estate: Tailored for the construction industry, offering

financial management tools like accounting and job costing.

5. Deltek Vision: An integrated project management tool that handles budgeting,

accounting, and other financial functions.

These tools are integral in enhancing project efficiency, managing resources effectively, and

ensuring financial oversight in engineering projects worldwide.

AI and software-based tools have significantly transformed financial management by

automating tasks, providing insights, and improving decision-making efficiency. Here’s a

comparison of How AI and other based software increase the efficiency of financial

management.

ASPECT AI TRADITIONAL SOFTWARE


1. Automation of routine tasks Automates complex tasks Automates basic tasks
(forecasting, budgeting, tax (invoicing, payroll), but lacks
calculation) and learns from learning or predictive
data to recommend capabilities.
improvements.
2. Data analysis and insights Uses predictive analytics to Relies on preset algorithms,
analyze large datasets, limited in data-driven insights,
detect, fraud, predict cash lacks predictive modeling or
flow, issues and suggest anomaly detection.
strategies.
3. Financial forecasting Analyzes historical and Requires manual input, less
external data for accurate dynamic, and struggles to
predictions and scenarios adjust to changing data.
simulations to asses risks.
4. Risk management Identifies and predicts Reactivate approach, tracks
financial risks in real- time by transaction but lacks real-
analyzing trends and time analysis or predictive
customer behavior. insights.
5. Cost and resource Optimizes resources by Focuses on tracking
optimization identifying inefficiencies and expenses, requires manual

25
under/ over-performing analysis for cost optimization,
areas, leading to cost which can be in
savings. timeconsuming.
6. Customer interaction Integrates chatbots and Typically handles by human
virtual assistant for agents, lacks personalization,
personalized service and which can result in slower
financial advice based on response times.
customer profiles.
7. Scalability Highly scalable, handles Requires more resources
large data volumes without (Staff, hardware) to scale
extra resources or manual effectively, less efficient with
input. larges data.

Based on the comparison of AI and Traditional software, AI enhances financial

management by automating complex tasks, offering advanced insights, and using predictive

analytics. It is a proactive tool that efficiently handles large datasets, scales effectively, and

provides valuable decision-making support. It provides a more advanced, dynamic, and

insightful approach to financial management. On the other hand, traditional software is effective

for routine tasks and automating basic processes but lacks the ability to learn, adapt, or provide

proactive insights, making it more reactive than forward-looking.

CHAPTER 3
26
METHODOLOGY

This study uses the most relevant style of research, which is correlational research with

an emphasis on quantitative methodologies in exploring the potential of artificial intelligence in

assisting with cost estimation in construction management, as an enhancement to traditional

budget management.

RESEARCH DESIGN

Correlational research is a statistical method that measures the relationship between two

or more variable. Its purpose is to address a specific engineering challenge

LOCALE OF THE STUDY

FIGURE 3.1 LOCATION

27
This study will conduct within Southern Oriental Mindoro, specifically focusing on the

municipality of Roxas, where construction activities are actively contributing to community’s

improvement.

RESPONDENTS OF THE STUDY

The respondents of the study will be selected to the construction company that operates

in the municipality of Roxas, Oriental Mindoro. The study will focus on those who are involved

directly in cost estimation, procurement, and project management. These individuals are

expected to have more than enough experience in the traditional methods of cost estimation

and good understanding of construction projects workflows. This study aims to examine to

examine the effectiveness of AI- powered material cost estimation tools in improving the

accuracy, efficiency and decision- making practices in construction management through

respondents’ experience and insights.

SAMPLING PROCEDURE

In this study the researcher will use cluster sampling method to select the respondents

for investigations of AI powered material cost estimation in construction management. The

researcher will conduct a study in the province of Oriental Mindoro specifically in the

municipality of Roxas. Using a cluster sampling, the researcher will randomly select a

construction company to test the effectiveness of the study. Every selected construction

company will be examining into two sub-group: first, will be using excel spreadsheet and the

other will be using AI powered material cost estimation method.

DATA GATHERING PROCEDURE

In this study, we will develop an artificial intelligence (AI) system using Machine Learning (ML)

with the consideration of its properties such as its algorithm learning through patterns of
28
existing data. We made an application centering ML as the core in which it takes a photograph

of a handwritten list of materials for a construction project and automatically generates the

total construction cost.

The methodology begins by gathering data, including handwritten material lists and their

corresponding market prices. The AI will be trained to read and interpret the handwritten text,

accurately identifying the materials and their quantities. These materials will then be linked to a

database of current market prices to compute the overall project cost. To validate the AI’s

performance, we will conduct testing using real-world datasets and cross-validation techniques

to ensure accuracy. A critical component of the methodology will be the comparison between

the AIgenerated estimates and traditional Excel-based cost estimation methods, where data is

manually entered, and costs are calculated using Excel formulas.

STATISTICAL ANALYSIS

A T-test is a statistical tool that is used to see if there is a significant difference between

the two methods in estimating. In this case, the two methods are the relationship from the Excel

and the AI-powered estimation. Based on the results from the T-test, the significant difference

between the two method was known. If the resulting value from the T-test is less than the

significance level, then the null hypothesis is rejected and therefore there would be a significant

difference in the relationship of the two methods.

By measuring factors such as time efficiency, accuracy, and error rates, the AI approach

will be directly compared to the Excel process. We will use statistical tests, a paired t-tests to

evaluate whether the AI provides a significant improvement in terms of speed and accuracy over

Excel. This comparative analysis will highlight the strengths and limitations of both systems in

automating construction cost estimation.

29
ETHICAL CONSIDERATIONS

The researcher should responsible to address the confidentiality of the

information gather.

Data privacy and security

The most relevant concerns; project- related data must handle in secure manners,

encrypted and with the consent of those data involved.

Informed consent

Obtains informed from all company providing data for the study. Clearly communicate

how data will be used, stored and protected.

Accuracy and reliabity

Transparency is essential and ensures that stakeholders understand how cost estimates

are generated with AI. Accuracy and reliabity of the AI system must always be validated to avoid

errors that may impact project budgets.

Bias and Fairness

Mitigating biases in the AI system to avoid skewed estimates that could unfairly benefit

or disadvantages any party. This involves carefully examining the data used to train the AI

system ensure it is diverse and comprehensive.

30
REFERENCES:

Lauzon, M., & Dela Cruz, A. (2021). "Data challenges in AI-based construction management in

the Philippines." Journal of Philippine Construction Engineering.

Panganiban, M., & Del Mundo, J. (2019). "The impact of AI on cost estimation in Philippine

construction." Philippine Journal of Civil Engineering.

Philippine Institute of Civil Engineers (PICE). (2021). "Smart construction: Integrating AI and BIM

in Philippine construction." PICE Annual Conference Proceedings.

Salazar, J., et al. (2020). "Machine learning in cost estimation for construction projects in the

Philippines." Journal of Construction Project Management.

Santos, R., et al. (2020). "AI and neural networks for material cost estimation in rural Philippine

construction projects." Journal of Civil Engineering and Technology.

Akinci, B., et al. (2018). "Applications of AI in the construction industry." Journal of Construction

Engineering and Management.

Becerik-Gerber, B., et al. (2012). "Applications of AI in construction project management."

Automation in Construction.

Pan, Y., & Zhang, L. (2021). "Roles of artificial intelligence in construction engineering and

management: A critical review and future trends." Automation in Construction, 131, 103939.

https://doi.org/10.1016/j.autcon.2021.103939

Xie, H., et al. (2020). "The future of AI in construction material management." Journal of

Intelligent & Robotic Systems.

Zhou, Z., et al. (2021). "Artificial Intelligence in construction: A review of current research and

future directions." Automation in Construction.

31
https://www.ijimt.org/vol8/717-MP0022.pdf

https://ww3.rics.org/uk/en/modus/built-environment/construction/is-the-cost-of-materials-

holdingback-construction-.html

https://ww3.rics.org/uk/en/modus/built-environment/construction/is-the-cost-of-materials-

holdingback-construction-.html

https://ww3.rics.org/uk/en/modus/built-environment/construction/is-the-cost-of-materials-

holdingback-construction-.html

https://www.ijimt.org/vol8/717-MP0022.pdf

https://ww3.rics.org/uk/en/modus/built-environment/construction/is-the-cost-of-materials-

holdingback-construction-.html

32

You might also like