Add ML/DM CRISP-DM

This commit is contained in:
2023-10-14 16:21:14 +02:00
parent 3c6370d738
commit 6068ed5518
3 changed files with 59 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 608 KiB

View File

@ -15,6 +15,7 @@
\DeclareAcronym{etl}{short=ETL, long=Extraction{,} Transformation{,} Loading}
\DeclareAcronym{dfm}{short=DFM, long=Dimensional Fact Model}
\DeclareAcronym{cdc}{short=CDC, long=Change Data Capture}
\DeclareAcronym{crisp}{short=CRISP-DM, long=Cross Industry Standard Process for Data Mining}
\begin{document}
@ -26,5 +27,6 @@
\input{sections/_intro.tex}
\input{sections/_data_warehouse.tex}
\input{sections/_data_lake.tex}
\input{sections/_crisp.tex}
\end{document}

View File

@ -0,0 +1,57 @@
\chapter{CRISP-DM}
\begin{description}
\item[\Acl{crisp}] \marginnote{\acs{crisp}}
Standardized process for data mining.
\begin{figure}[ht]
\centering
\includegraphics[width=0.45\textwidth]{img/crisp.png}
\caption{\ac{crisp} workflow}
\end{figure}
\end{description}
\section{Business understanding}
\begin{itemize}
\item Determine the objective and the success criteria.
\marginnote{Business understanding}
\item Feasibility study.
\item Produce a plan.
\end{itemize}
\section{Data understanding}
\begin{itemize}
\item Determine the available (raw) data.
\marginnote{Data understanding}
\item Determine the cost of the data.
\item Collect, describe, explore and verify data.
\end{itemize}
\section{Data preparation}
\begin{itemize}
\item Data cleaning.
\marginnote{Data preparation}
\item Data transformations.
\end{itemize}
\section{Modelling}
\begin{itemize}
\item Select modelling technique.
\marginnote{Modelling}
\item Build/train the model.
\end{itemize}
\section{Evaluation}
\begin{itemize}
\item Evaluate results.
\marginnote{Evaluation}
\item Review process.
\end{itemize}
\section{Deployment}
\begin{itemize}
\item Plan deployment.
\marginnote{Deployment}
\item Plan monitoring and maintenance.
\item Final report and review.
\end{itemize}