DATA MINING and MACHINE LEARNING. PREDICTIVE TECHNIQUES: ENSEMBLE METHODS, BOOSTING, BAGGING, RANDOM FOREST, DECISION TREES and REGRESSION TREES.: Examples with MATLAB
Yna Gabrielle Foronda Francis Maurice Miranda Jonathan Pelon
Objective Matrix (First Version)
Objectives Methodology Expected Outputs
Collect, prepare, and - Data Collection (web - Raw dataset of web
understand the data for scraping from scraped data (csv) the modeling. wundergound.com) - Pre-processed - Data Pre-Processing dataset (csv) - Exploratory Data - EDA Visualizations Analysis and Interpretations
Conduct the modeling for - Finalize algorithms - List of algorithms
anomaly detection using to be utilized - Modeling the defined algorithms - Conduct the specifications experiments/train (dataset splits, the models using the algorithm different algorithms descriptions, etc.) - Visualizations produced by the algorithms showing the anomalies detected
Identify insights on the - Analysis of the Presentation and discussion
outliers of the weather visualizations of the following information: data. - Formulate a - Percentage of outliers conclusion over total instances - Months with most number abnormal weather occurrences - Patterns/trends the outliers show - Tabulation of detected anomalies Compare the results of - Perform evaluation - Comparative Analysis the different algorithms methods on each Table of the applied using key performance algorithm algorithms measures. - Formulate a - Visualizations of the conclusion evaluations of each algorithm - Conclusion on best algorithm
DATA MINING and MACHINE LEARNING. PREDICTIVE TECHNIQUES: ENSEMBLE METHODS, BOOSTING, BAGGING, RANDOM FOREST, DECISION TREES and REGRESSION TREES.: Examples with MATLAB