IBM 0A079G - Introduction to Machine Learning Models Using IBM SPSS Modeler (V18.2) - Seminar / Kurs von PROKODA GmbH

Knowledge of your business requirements

Inhalte

Course Outline

Introduction to machine learning models· Taxonomy of machine learning models· Identify measurement levels· Taxonomy of supervised models· Build and apply models in IBM SPSS ModelerSupervised models: Decision trees - CHAID· CHAID basics for categorical targets· Include categorical and continuous predictors· CHAID basics for continuous targets· Treatment of missing valuesSupervised models: Decision trees - C&R Tree· C&R Tree basics for categorical targets· Include categorical and continuous predictors· C&R Tree basics for continuous targets· Treatment of missing valuesEvaluation measures for supervised models· Evaluation measures for categorical targets· Evaluation measures for continuous targetsSupervised models: Statistical models for continuous targets - Linear regression· Linear regression basics· Include categorical predictors· Treatment of missing valuesSupervised models: Statistical models for categorical targets - Logistic regression· Logistic regression basics· Include categorical predictors· Treatment of missing valuesSupervised models: Black box models - Neural networks· Neural network basics· Include categorical and continuous predictors· Treatment of missing valuesSupervised models: Black box models - Ensemble models· Ensemble models basics· Improve accuracy and generalizability by boosting and bagging· Ensemble the best modelsUnsupervised models: K-Means and Kohonen· K-Means basics· Include categorical inputs in K-Means· Treatment of missing values in K-Means· Kohonen networks basics· Treatment of missing values in KohonenUnsupervised models: TwoStep and Anomaly detection· TwoStep basics· TwoStep assumptions· Find the best segmentation model automatically· Anomaly detection basics· Treatment of missing valuesAssociation models: Apriori· Apriori basics· Evaluation measures· Treatment of missing valuesAssociation models: Sequence detection· Sequence detection basics· Treatment of missing valuesPreparing data for modeling· Examine the quality of the data· Select important predictors· Balance the data

Objective

Introduction to machine learning models · Taxonomy of machine learning models · Identify measurement levels · Taxonomy of supervised models · Build and apply models in IBM SPSS Modeler

Supervised models: Decision trees - CHAID · CHAID basics for categorical targets · Include categorical and continuous predictors · CHAID basics for continuous targets · Treatment of missing values

Supervised models: Decision trees - C&R Tree

· C&R Tree basics for categorical targets · Include categorical and continuous predictors · C&R Tree basics for continuous targets · Treatment of missing values

Evaluation measures for supervised models · Evaluation measures for categorical targets · Evaluation measures for continuous targets

Supervised models: Statistical models for continuous targets - Linear regression · Linear regression basics · Include categorical predictors · Treatment of missing values

Supervised models: Statistical models for categorical targets - Logistic regression · Logistic regression basics · Include categorical predictors · Treatment of missing values

Association models: Sequence detection · Sequence detection basics · Treatment of missing values

Supervised models: Black box models - Neural networks · Neural network basics · Include categorical and continuous predictors · Treatment of missing values

Supervised models: Black box models - Ensemble models · Ensemble models basics · Improve accuracy and generalizability by boosting and bagging · Ensemble the best models

Unsupervised models: K-Means and Kohonen · K-Means basics · Include categorical inputs in K-Means · Treatment of missing values in K-Means · Kohonen networks basics · Treatment of missing values in Kohonen

Unsupervised models: TwoStep and Anomaly detection · TwoStep basics · TwoStep assumptions · Find the best segmentation model automatically · Anomaly detection basics · Treatment of missing values

Association models: Apriori · Apriori basics · Evaluation measures · Treatment of missing values

Preparing data for modeling · Examine the quality of the data · Select important predictors · Balance the data

Hinweise

Unterrichtsmethode

presentation, discussion, hands-on exercises

Dieses Training bieten wir in Kooperation mit der Integrata AG an.

Termine und Orte

Datum Uhrzeit Dauer Preis
Hamburg, DE
26.11.2020 - 27.11.2020 09:00 - 16:00 Uhr 16 h Jetzt buchen ›
München, DE
26.11.2020 - 27.11.2020 09:00 - 16:00 Uhr 16 h Jetzt buchen ›

SG-Seminar-Nr.: 5505837

Termine

  • 26.11.2020 - 27.11.2020

    Hamburg, DE

    München, DE

Preise inkl. MwSt. Es können Gebühren anfallen. Für eine exakte Preisauskunft wählen Sie bitte einen Termin aus.

Jetzt buchen ›
Seminar merken ›

Semigator berücksichtigt

  • Frühbucher-Preise
  • Last-Minute-Preise
  • Gruppenkonditionen

und verfügt über Sonderkonditionen mit einigen Anbietern.

Der Anbieter ist für den Inhalt verantwortlich.

Über Semigator mehr erfahren

  • Anbietervergleich von über 1.500 Seminaranbietern
  • Vollständige Veranstaltungsinformationen
  • Schnellbuchung
  • Persönlicher Service
Datum Uhrzeit Dauer Preis
Hamburg, DE
26.11.2020 - 27.11.2020 09:00 - 16:00 Uhr 16 h Jetzt buchen ›
München, DE
26.11.2020 - 27.11.2020 09:00 - 16:00 Uhr 16 h Jetzt buchen ›