Declarative Modeling for Machine Learning and Data Mining -- Recent Developments in Pattern Mining -- Exploring Sequential Data -- Large Scale Spectral Clustering Using Resistance Distance and Spielman-Teng Solvers -- Prediction of Quantiles by Statistical Learning and Application to GDP Forecasting -- Policy Search in a Space of Simple Closed-form Formulas: Towards Interpretability of Reinforcement Learning -- Towards Finding Relational Redescriptions -- Descriptive Modeling of Systemic Banking Crises -- A Trim Distance between Positions in Nucleotide Sequences -- Data Squashing for HSV Subimages by an Autonomous Mobile Robot -- Cohesive Co-evolution Patterns in Dynamic Attributed Graphs -- Efficient Redundancy Reduced Subgroup Discovery via Quadratic Programming -- HCAC: Semi-supervised Hierarchical Clustering Using Confidence- Based Active Learning -- LF-CARS: A Loose Fragment-Based Consensus Clustering Algorithm with a Robust Similarity -- Fast Approximation Algorithm for the 1-Median Problem -- Online Co-regularized Algorithms -- Fast Progressive Training of Mixture Models for Model Selection -- Including Spatial Relations and Scales within Sequential Pattern Extraction -- Predicting Ramp Events with a Stream-Based HMM Framework -- Burst Detection in a Sequence of Tweets Based on Information Diffusion Model -- Error-Correcting Output Codes as a Transformation from Multi-Class to Multi-Label Prediction -- An Assessment on Loan Performance from Combined Quantitative and Qualitative Data in XML -- Structural Change Pattern Mining Based on Constrained Maximal k-Plex Search -- Enhancing Patent Expertise through Automatic Matching with Scientific Papers -- Soft Threshold Constraints for Pattern Mining.

This book constitutes the refereed proceedings of the 15th International Conference on Discovery Science, DS 2012, held in Lyon, France, in October 2012. The 22 papers presented in this volume were carefully reviewed and selected from 46 submissions. The field of discovery science aims at inducing and validating new scientific hypotheses from data. The scope of this conference includes the development and analysis of methods for automatic scientific knowledge discovery, machine learning, intelligent data analysis, theory of learning, tools for supporting the human process of discovery in science, as well as their application to knowledge discovery.