Update Lit

Lit

@@ -1,72 +1,64 @@
 \documentclass{article}
-\usepackage{amsmath}
+\usepackage{algorithm}
+\usepackage{algorithmic}
 
 \begin{document}
 
-\section*{Outlier/Cluster Detection Algorithm for Bank 10-K Items (Updated)}
+\section*{Algorithm: Outlier/Cluster Detection with Topic Distributions}
 
-\textbf{Algorithm 1: Outlier/Cluster Detection Algorithm for Bank 10-K Items (Full Scope)}
+\begin{algorithm}
+\caption{Outlier/Cluster Detection Algorithm for Bank 10-K Items}
+\begin{algorithmic}[1]
+\REQUIRE Text data for Item $i$ of bank $j$ over years $t = 1, \dots, T$.
+\ENSURE Continuous outlier and cluster scores normalized by holding company asset size.
 
+\FORALL{years $t \in \{1, \dots, T\}$}
+    \FORALL{banks $j$}
+        \STATE Extract text $I_{i,j,t}$ for Item $i$ of bank $j$ at year $t$.
+        \STATE Split $I_{i,j,t}$ into semantic chunks or paragraphs.
+        \STATE Clean $I_{i,j,t}$ by removing stopwords and performing preprocessing.
+        \STATE Build topic model using BERTopic:
+        \begin{enumerate}
+            \item Generate topics $k$ and embeddings $v_{k}$ for each chunk.
+            \item Apply hierarchical clustering to group topics into parent topics.
+            \item Select parent topics based on hierarchical levels or topic coverage.
+        \end{enumerate}
+        \STATE Compute topic distributions $D_{i,j,t}$ as percentages:
+        \begin{enumerate}
+            \item Normalize counts of topics by total topic occurrences in year $t$.
+            \item Optionally compute weighted topic distributions based on order of topics discussed.
+        \end{enumerate}
+    \ENDFOR
+\ENDFOR
+
+\STATE Aggregate topic distributions $D_{i,j,t}$ over all years $t$ for each bank $j$.
+
+\STATE Compute embedding matrix $V_{i,j}$ using aggregated topic distributions.
+
+\STATE Apply clustering and outlier detection:
 \begin{enumerate}
-    \item \textbf{Input:}
-    \begin{itemize}
-        \item Item $i$ (e.g., ``Item 3: Legal Proceedings'') for bank $j$ over years $t = 1, \dots, T$.
-    \end{itemize}
-
-    \item \textbf{Output:}
+    \item Use KMeans clustering to determine optimal clusters $k$ using silhouette score.
+    \item Test for multivariate normality of $V_{i,j}$:
     \begin{itemize}
-        \item Continuous outlier and cluster scores normalized by holding company asset size.
+        \item \textbf{If normality is True:}
+        \begin{enumerate}
+            \item Apply robust Mahalanobis distance using Minimum Covariance Determinant (MCD).
+            \item Apply Local Outlier Factor (LOF).
+            \item Flag points as outliers if identified by both Mahalanobis distance and LOF.
+        \end{enumerate}
+        \item \textbf{Else:}
+        \begin{enumerate}
+            \item Apply only LOF for outlier detection.
+        \end{enumerate}
     \end{itemize}
-
-    \item \textbf{For each} $t$ in years $T$:
-    \begin{enumerate}
-        \item Extract text $I_{i,j,t}$ for Item $i$ of bank $j$ at time $t$.
-        \item Split $I_{i,j,t}$ into semantic chunks of size $n$ or paragraphs.
-        \item Clean $I_{i,j,t}$ by removing stopwords and preprocessing text.
-        \item Build a topic model using BERTopic:
-        \begin{itemize}
-            \item Generate topics $k$ and topic embeddings $v_{k}$ for each chunk.
-            \item Apply hierarchical clustering on topic embeddings to reduce dimensionality:
-            \begin{itemize}
-                \item Group similar topics into higher-level parent topics.
-                \item Select parent topics based on hierarchical levels or topic coverage.
-            \end{itemize}
-        \end{itemize}
-        \item Compute topic distributions $D_{i,j,t}$ as percentages rather than counts:
-        \begin{itemize}
-            \item Normalize counts of topics for each bank $j$ by total topic occurrences in year $t$.
-            \item Optionally compute weighted topic distributions based on order of topic discussion.
-        \end{itemize}
-    \end{enumerate}
-    \item \textbf{End for.}
-
-    \item Aggregate topic distributions over years and compute embeddings $v_{i,j}$ for each bank:
-    \begin{itemize}
-        \item Use embeddings of topic distributions as input data.
-    \end{itemize}
-
-    \item Apply outlier and clustering detection on $v_{i,j}$:
-    \begin{enumerate}
-        \item Apply KMeans clustering to determine optimal clusters $k$ using silhouette score.
-        \item Test for multivariate normality of $v_{i,j}$:
-        \begin{itemize}
-            \item \textbf{If normality is True:}
-            \begin{itemize}
-                \item Apply robust Mahalanobis distance using Minimum Covariance Determinant (MCD).
-                \item Apply Local Outlier Factor (LOF) on $v_{i,j}$.
-                \item Flag points as outliers if identified by both Mahalanobis distance and LOF.
-            \end{itemize}
-            \item \textbf{Else:}
-            \begin{itemize}
-                \item Apply LOF only, as Mahalanobis distance assumes normality.
-            \end{itemize}
-        \end{itemize}
-    \end{enumerate}
-
-    \item Convert discrete outlier and cluster outputs into continuous scores.
-    \item Normalize outlier and cluster scores by holding company asset size.
 \end{enumerate}
 
-\textbf{End Algorithm.}
+\STATE Convert discrete outlier and cluster outputs into continuous scores.
+\STATE Normalize outlier and cluster scores by holding company asset size.
+
+\RETURN Continuous outlier and cluster scores.
+
+\end{algorithmic}
+\end{algorithm}
 
 \end{document}