srs-document/Chapters/Chapter_02.tex

% Some LaTeX commands I define for my own nomenclature.
% If you have to, it's better to change nomenclature once here than in a 
% million places throughout your thesis!
\newcommand{\package}[1]{\textbf{#1}} % package names in bold text
\newcommand{\cmmd}[1]{\textbackslash\texttt{#1}} % command name in tt font 


%======================================================================
\chapter{Literature Review and Related Work}
%======================================================================

% This is Chapter 02!
% Author \cite{al2020generalizing} presented....
% Author \cite{elayan2021digital} proposed...
% Author \cite{10223206} implemented...

This chapter presents a review of existing platforms in the domain of real estate analytics and information systems. 
This review includes both international and Thai platforms, their features, strengths, and limitations. 
The analysis establishes the current state of real estate information platforms and identifies opportunities 
for the BorBann platform to address unmet needs in the Thai market.

\section{Competitor Analysis}

Many real estate platforms primarily function as property listing aggregators rather than comprehensive information systems. 
Their features support transaction facilitation through showcasing available properties, while offering limited analytical tools for market understanding.
 However, platforms like House Canary represent exceptions, operating specifically as information systems that provide investors with
  data analytics and market insights to support evidence-based decision-making in real estate investments.

\begin{table}[htbp]
\centering
\renewcommand{\arraystretch}{1.3}
\resizebox{0.9\textwidth}{!}{ % Adjust width to 90% of text width
    \begin{tabular}{>{\raggedright\arraybackslash}p{0.35\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}}
        \toprule \rowcolor[gray]{0.9} 
        \textbf{Feature}                              & \textbf{BorBann (Proposed)} & \textbf{DDProperty} & \textbf{Hipflat} & \textbf{House Canary} & \textbf{Zillow} \\
        \midrule
        \textbf{Customizable Automated Data Integration Pipeline}  & \textbf{Yes} & No              & No                 & No                 & No                 \\
        \addlinespace \textbf{Retrain Model with Data from Pipeline} & \textbf{Yes} & No              & No                & No    & No  \\
        \addlinespace \textbf{Local Contextual Analytics} & \textbf{Yes} & No              & No                & Yes (Not optimized for Thailand)  & Yes (Not optimized for Thailand)  \\
        \addlinespace \textbf{Explainable Price Prediction Model} & \textbf{Yes} & No              & No                 & No                  & No                \\
        \addlinespace \textbf{Geospatial Visualization}        & \textbf{Yes} & Yes              & Yes                 & Yes                 & Yes                \\
        \bottomrule
    \end{tabular}
}
\caption{Feature Comparison: BorBann vs Other Platforms}
\label{tab:feature-comparison}
\end{table}

Table \ref{tab:feature-comparison} demonstrates BorBann's technical advantages in the real estate analytics market. While all platforms offer geospatial visualization,
 BorBann's implementation includes advanced analytics like climate assessment, matching international platforms but surpassing local Thai competitors.
  BorBann's automated data integration pipeline collects analytics-ready data automatically, unlike Thai platforms that rely on user inputs. Also, user can use that data to create their custom models.
   For local contextual analytics, BorBann provides Thailand-optimized insights including weather patterns and population density,
    whereas DDProperty/Hipflat only show basic nearby facilities, and international platforms lack Thailand-specific optimization.
     Most distinctively, BorBann's price prediction model prioritizes explainability and interpretability,
      revealing the reasoning behind valuations rather than presenting opaque predictions like competing platforms.


\begin{table}[htbp]
\centering
\renewcommand{\arraystretch}{1.3}
\resizebox{0.9\textwidth}{!}{
    \begin{tabular}{>{\raggedright\arraybackslash}p{0.25\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}>{\centering\arraybackslash}p{0.15\textwidth}}
        \toprule \rowcolor[gray]{0.9} 
        \textbf{Technical Aspect} & \textbf{DDProperty} & \textbf{Hipflat} & \textbf{House Canary} & \textbf{Zillow} & \textbf{BorBann (Proposed)} \\
        \midrule
        \textbf{Data Sources} & User-submitted, Proprietary & User-submitted, Proprietary & Proprietary & Multiple Sources, Proprietary & Open Data, User-submitted \\
        \addlinespace \rowcolor[gray]{0.95} \textbf{ML Implementation} & Basic Prediction & None & Black-box Models & Black-box Models & Explainable Models \\
        \bottomrule
    \end{tabular}
}
\caption{Comprehensive Technical Comparison}
\label{tab:competitor-analysis}
\end{table}

Table \ref{tab:competitor-analysis} highlights key technical differences between BorBann and competing platforms.
 For data sources, while competitors rely heavily on government or user-submitted data, BorBann uniquely leverages open data combined with
  APIs to build a more comprehensive dataset. Regarding machine learning, BorBann distinguishes itself by implementing explainable models,
   providing transparency in its predictions. This contrasts with DDProperty's basic prediction capabilities, Hipflat's complete lack of ML features,
    and the black-box approaches of House Canary and Zillow where prediction logic remains hidden from users.

% \section{Literature Review}