diff --git a/src/ainotes.cls b/src/ainotes.cls index 388f728..0323a80 100644 --- a/src/ainotes.cls +++ b/src/ainotes.cls @@ -16,6 +16,8 @@ \usepackage{scrlayer-scrpage} \usepackage{scrhack, algorithm, listings} \usepackage{array, makecell} +\usepackage{acro} + \geometry{ margin=3cm, lmargin=1.5cm, rmargin=4.5cm, marginparwidth=3cm } \hypersetup{ colorlinks, citecolor=black, filecolor=black, linkcolor=black, urlcolor=black, linktoc=all } diff --git a/src/machine-learning-and-data-mining/ainotes.cls b/src/machine-learning-and-data-mining/ainotes.cls new file mode 120000 index 0000000..c22704b --- /dev/null +++ b/src/machine-learning-and-data-mining/ainotes.cls @@ -0,0 +1 @@ +../ainotes.cls \ No newline at end of file diff --git a/src/machine-learning-and-data-mining/img/data_mining_process.png b/src/machine-learning-and-data-mining/img/data_mining_process.png new file mode 100644 index 0000000..a8fe347 Binary files /dev/null and b/src/machine-learning-and-data-mining/img/data_mining_process.png differ diff --git a/src/machine-learning-and-data-mining/main.tex b/src/machine-learning-and-data-mining/main.tex new file mode 100644 index 0000000..965eb35 --- /dev/null +++ b/src/machine-learning-and-data-mining/main.tex @@ -0,0 +1,26 @@ +\documentclass[11pt]{ainotes} + +\title{Machine Learning and Data Mining} +\date{2023 -- 2024} + +\DeclareAcronym{oltp}{short=OLTP, long=On-Line Transaction Processing} +\DeclareAcronym{erp}{short=ERP, long=Enterprise Resource Planning} +\DeclareAcronym{mis}{short=MIS, long=Management Information System} +\DeclareAcronym{dss}{short=DSS, long=Decision Support System} +\DeclareAcronym{eis}{short=EIS, long=Executive Information System} +\DeclareAcronym{olap}{short=OLAP, long=On-Line Analysical Processing} +\DeclareAcronym{bi}{short=BI, long=Business Intelligence} +\DeclareAcronym{dwh}{short=DWH, long=Data Warehouse} +\DeclareAcronym{dm}{short=DM, long=Data Mart} + + +\begin{document} + + \makenotesfront + \printacronyms + \newpage + + \input{sections/_intro.tex} + \input{sections/_bi.tex} + +\end{document} \ No newline at end of file diff --git a/src/machine-learning-and-data-mining/sections/_bi.tex b/src/machine-learning-and-data-mining/sections/_bi.tex new file mode 100644 index 0000000..f91f081 --- /dev/null +++ b/src/machine-learning-and-data-mining/sections/_bi.tex @@ -0,0 +1,22 @@ +\chapter{Business Intelligence} + + +\begin{description} + \item[\Acl{bi}] \marginnote{\Acl{bi}} + Transform raw data into information. + Deliver the right information to the right people at the right time through the right channel. + + \item[\Ac{dwh}] \marginnote{\Acl{dwh}} + Optimized repository that stores information for decision making processes. + \Acp{dwh} are a specific type of \ac{dss}. + + Features: + \begin{itemize} + \item Subject-oriented: focused on enterprise specific concepts. + \item Integrates data from different sources and provides an unified view. + \item Non-volatile storage with change tracking. + \end{itemize} + + \item[\Ac{dm}] \marginnote{\Acl{dm}} + Subset of the primary \ac{dwh} with information relevant to a specific business area. +\end{description} \ No newline at end of file diff --git a/src/machine-learning-and-data-mining/sections/_intro.tex b/src/machine-learning-and-data-mining/sections/_intro.tex new file mode 100644 index 0000000..2c372d5 --- /dev/null +++ b/src/machine-learning-and-data-mining/sections/_intro.tex @@ -0,0 +1,98 @@ +\chapter{Introduction} + + +\section{Data} + +\begin{description} + \item[Data] \marginnote{Data} + Collection of raw values. + + \item[Information] \marginnote{Information} + Organized data (e.g. relationships, context, \dots). + + \item[Knowledge] \marginnote{Knowledge} + Understanding information. +\end{description} + + +\subsection{Data sources} +\begin{description} + \item[Transaction] \marginnote{Transaction} + Business event that generates or modifies data in an information system (e.g. database). + + \item[Signal] \marginnote{Signal} + Measure produced by a sensor. + + \item[External subjects] +\end{description} + + +\subsection{Software} +\begin{description} + \item[\Ac{oltp}] \marginnote{\Acl{oltp}} + Class of programs to support transaction oriented applications and data storage. + Suitable for real-time applications. + + \item[\Ac{erp}] \marginnote{\Acl{erp}} + Integrated system to manage all the processes of a business. + Uses a shared database for all applications. + Suitable for real-time applications. +\end{description} + + +\subsection{Insight} +Decision can be classified as: +\begin{descriptionlist} + \item[Structured] \marginnote{Structured decision} + Established and well understood situations. + What is needed is known. + \item[Unstructured] \marginnote{Unstructured decision} + Unplanned and unclear situations. + What is needed for the decision is unknown. +\end{descriptionlist} + +Different levels of insight can be extracted by: +\begin{descriptionlist} + \item[\Ac{mis}] \marginnote{\Acl{mis}} + Standardized reporting system built on existing \ac{oltp}. + Used for structured decisions. + + \item[\Ac{dss}] \marginnote{\Acl{dss}} + Analytical system to provide support for unstructured decisions. + + \item[\Ac{eis}] \marginnote{\Acl{eis}} + Formulate high level decisions that impact the organization. + + \item[\Ac{olap}] \marginnote{\Acl{olap}} + Grouped analysis of multidimensional data. + Involves large amount of data. + + \item[\Ac{bi}] \marginnote{\Acl{bi}} + Applications, infrastructure, tools and best practices to analyze information. +\end{descriptionlist} + + + +\begin{description} + \item[Big data] \marginnote{Big data} + Large and/or complex and/or fast changing collection of data that traditional DBMSs are unable to process. + \begin{description} + \item[Structured] e.g. relational tables. + \item[Unstructured] e.g. videos. + \item[Semi-structured] e.g. JSON. + \end{description} + + \item[Anaylitics] \marginnote{Anaylitics} + Structured decision driven by data. + + \item[Data mining] \marginnote{Data mining} + Discovery process for unstructured decisions. + \begin{figure}[ht] + \centering + \includegraphics[width=0.8\textwidth]{img/data_mining_process.png} + \caption{Data mining process} + \end{figure} + + \item[Machine learning] \marginnote{Machine learning} + Learning models and algorithms that allow to extract patterns from data. +\end{description} \ No newline at end of file