KEMBAR78
Machine Learnig - Ensembling Model - Lect 9 | PDF | Machine Learning | Statistical Classification
Scribd
Upload
25 views10 pages

Machine Learnig - Ensembling Model - Lect 9

The document discusses ensemble algorithms in machine learning, highlighting their ability to improve performance, accuracy, and robustness by combining predictions from multiple models. It outlines different types of ensemble methods, including bagging, boosting, stacking, and voting, along with their common algorithms. Stacking is emphasized as a technique that combines multiple models to enhance predictive performance through a meta-model.

Uploaded by

Isaac Acquah
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
25 views10 pages

Machine Learnig - Ensembling Model - Lect 9

The document discusses ensemble algorithms in machine learning, highlighting their ability to improve performance, accuracy, and robustness by combining predictions from multiple models. It outlines different types of ensemble methods, including bagging, boosting, stacking, and voting, along with their common algorithms. Stacking is emphasized as a technique that combines multiple models to enhance predictive performance through a meta-model.

Uploaded by

Isaac Acquah
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

Machnine Learning (ENSEMBLING MODELS)

Dr. Nana Yaw Duodu


Computer Science Department
Accra Technical University
ENSEMBLE ALGORITHMS IN MACHINE LEARNING
COMPUTER SCIENCE DEPARTMENT

➢Machine learning is a powerful method inside the broader field of data


science.
➢It enables data scientists to predict outcomes, classify data, detect patterns, and
automate decisions based on historical or real-time data.

15 July 2025 FACULTY OF APPLIED SCIENCES 2


ENSEMBLE ALGORITHMS IN MACHINE LEARNING
COMPUTER SCIENCE DEPARTMENT

➢Machine learning is a powerful method inside the broader field of data


science.
➢It enables data scientists to predict outcomes, classify data, detect patterns, and
automate decisions based on historical or real-time data.

➢Ensemble algorithms combine predictions from multiple models to improve


performance, accuracy, and robustness. They are especially useful when
individual models (weak learners) do not perform well on their own.

15 July 2025 FACULTY OF APPLIED SCIENCES 3


Feature Selection and Engineering
COMPUTER SCIENCE DEPARTMENT

• Stacking and bagging are both ensemble learning techniques used to improve
model performance, but they differ in how they combine individual models.

15 July 2025 FACULTY OF APPLIED SCIENCES 4


TYPES OF ENSEMBLE ALGORITHMS
COMPUTER SCIENCE DEPARTMENT

Type Description Common Algorithms

Builds models in parallel and averages results to


Bagging Random Forest
reduce variance.

Builds models sequentially, each correcting errors AdaBoost, Gradient Boosting, XGBoost,
Boosting
of the previous one. LightGBM

Combines predictions of multiple models using a


Stacking Model Blending (custom)
meta-model.

Combines multiple models by majority vote or


Voting Hard Voting / Soft Voting Classifier
average.
15 July 2025 FACULTY OF APPLIED SCIENCES 5
COMPUTER SCIENCE DEPARTMENT

15 July 2025 FACULTY OF APPLIED SCIENCES 6


COMPUTER SCIENCE DEPARTMENT

15 July 2025 FACULTY OF APPLIED SCIENCES 7


COMPUTER SCIENCE DEPARTMENT

15 July 2025 FACULTY OF APPLIED SCIENCES 8


STACKING
COMPUTER SCIENCE DEPARTMENT

• Stacking (Stacked Generalization) is an ensemble learning technique that aims


to combine multiple models to improve predictive performance.

• It involves the following steps:


• Base Models: Training multiple models (level-0 models) on the same dataset.

• Meta-Model: Training a new model (level-1 or meta-model) to combine the predictions of


the base models. Using the predictions of the base models as input features for the meta-
model.

15 July 2025 FACULTY OF APPLIED SCIENCES 9


THANK You !!

15 July 2025 FACULTY OF APPLIED SCIENCES 10

You might also like