Lehrstuhl für Angewandte Softwaretechnik
Chair for Applied Software Engineering

Extracting Knowledge From Unstructured Data -

Applications of Machine Learning in Software Engineering

Master Seminar (IN2107, IN8901)


This seminar focuses on techniques from machine learning and data mining, and surveys their application in software engineering.
In particular, the seminar investigates how such techniques aid program comprehension, help to analyze and interpret large amounts of user input, and facilitate the extraction of relevant knowledge from unstructured data.

During the seminar each participant will present a machine learning technique including a particular application in software engineering.

Organizational Issues

  • The presentations will take place from 12:30 to 16:30 on:
    • Thu, February 2 in room 01.07.058
    • Fri, February 3 in room 01.07.014
  • In case of any questions please write an e-mail to pagano (at) in.tum.de.


Thursday, February 2, 2012 - room 01.07.058
Time Paper Title Authors Used Technique Presented by
12:30 Summarizing the Content of Large Traces to Facilitate the Understanding of the Behaviour of a Software System Hamou-Lhadj and Lethbridge Statistics Saburo Okita
13:15 An information retrieval approach to concept location in source code Marcus et al. Latent Semantic Indexing Chakajkla Jesdabodi
14:00 Design pattern mining enhanced by machine learning Ference et al. Decision trees, neural networks Hassaan Nasir
14:45 How Long will it Take to Fix This Bug? Weiß et al. a-kNN Miguel Fernando Cabrera
15:30 Duplicate Bug Reports Considered Harmful... Really? Bettenburg et al. SVM Bernd Schultze

Friday, February 3, 2012 - room 01.07.014
Time Paper Title Authors Used Technique Presented by
12:30 A Recommender System for Requirements Elicitation in Large-Scale Software Projects Castro-Herrera et al. Collaborative Filtering Stefan Theiner
13:15 Towards an Intelligent Code Search Engine Kim et al. Summarization based on AST information and K-means Thomas Rothoerl
14:00 On-demand Feature Recommendations Derived from Mining Public Product Descriptions Dumitru et al. Incremental Diffusive Clustering Nadeem Ahmed
14:45 Classification of Software Behaviors for Failure Detection: A Discriminative Pattern Mining Approach Lo et al. Frequent iterative pattern mining Ilira Troshani
15:30 Discriminative Pattern Mining in Software Fault Detection Di Fatta et al. Frequent pattern mining: FREQT Mahmut Kafkas


Grades will be based on the following criteria:

  • Ability to do independent research
  • Oral presentation
  • Written term paper
  • Active participation in all the other presentations (compulsory attendance)


Teaching Assistants