Introduce students to the main components of the data mining process, such as data preparation, feature extraction and feature selection, machine learning algorithms for building predictive and descriptive analytics models,evaluation of data analytics models.

1. What is data mining; what is the relation between data mining, data analytics, data science; why data mining; cross-industry standard process (CRISP-DM); data mining workflows. 2. Data pre-processing: feature extraction, data cleaning, handling missing data, methods for identifying outliers, data transformation. 3. Methods for feature selection: filter, wrapper and embedded methods. 4. Styles of machine learning for data mining: supervised vs. unsupervised learning, classification, numeric prediction, clustering, association learning. 5. Algorithms for building predictive and descriptive analytics models: a. Predictive modelling algorithms for classification and numeric prediction, such as OneR, ID3, C4.5, Naïve Bayes, k-NN, Prism, SVM, linear regression, logistic regression, Perceptron, Winnow. b. Descriptive modelling algorithms for clustering and association learning, such as k-means, apriori, max-miner. 6. Evaluation of predictive and descriptive analytics models: Holdout and cross-validation, cost-benefit analysis, user feedback. 7. Visual analytics: methodology and workflow. 8. Case studies in subdomains, such as sentiment analysis, item/service ranking recommendation, image classification, etc. 9. Practical use of data mining platforms for building data mining workflows and training predictive and descriptive analytics models.

1. Summarise the main elements of the data mining workflow. 2. Differentiate predictive from descriptive analytics in terms of methods and output. 3. Recognise and describe at least one algorithm in each of the four categories: classification, numeric prediction, clustering, association learning. 5. Construct data mining workflows with the use of data mining software for training of predictive and descriptive analytics models. 6. Analyse the results of machine learning algorithms. 7. Recognise the role of data visualisation in the data mining process.

1. Discuss the benefits of data mining for industry and society.

N/A

The module is taught in the form of lectures and lab practice. The material delivered in lectures is practices with a data mining software platform in a computer lab.