Efficient clustering algorithms, such as k -Means, are often used in practice because they scale well for large datasets. However, they are only able to detect simple data characteristics. Ensemble clustering can overcome this limitation by combining multiple results of efficient algorithms. However, analysts face several challenges when applying ensemble clustering, i. e., analysts struggle to (a) efficiently generate an ensemble and (b) combine the ensemble using a suitable consensus function with a corresponding hyperparameter setting. In this paper, we propose EffEns, an efficient ensemble clustering approach to address these challenges. Our approach relies on meta-learning to learn about dataset characteristics and the correlation between generated base clusterings and the performance of consensus functions. We apply the learned knowledge to generate appropriate ensembles and select a suitable consensus function to combine their results. Further, we use a state-of-the-art optimization technique to tune the hyperparameters of the selected consensus function. Our comprehensive evaluation on synthetic and real-world datasets demonstrates that EffEns significantly outperforms state-of-the-art approaches w.r.t. accuracy and runtime.

Analysts often struggle with the combined algorithm selection and hyperparameter optimization problem, a.k.a. CASH problem in literature. Typically, they execute several algorithms with varying hyperparameter settings to find configurations that show valuable results. Efficiently finding these configurations is a major challenge. In clustering analyses, analysts face the additional challenge to select a cluster validity index that allows them to evaluate clustering results in a purely unsupervised fashion. Many different cluster validity indices exist and each one has its benefits depending on the dataset characteristics. While experienced analysts might address these challenges using their domain knowledge and experience, especially novice analysts struggle with them. In this paper, we propose a new meta-learning approach to address these challenges. Our approach uses knowledge from past clustering evaluations to apply strategies that experienced analysts would exploit. In particular, we use meta-learning to (a) select a suitable clustering validity index, (b) efficiently select well-performing clustering algorithm and hyperparameter configurations, and (c) reduce the search space to suitable clustering algorithms. In the evaluation, we show that our approach significantly outperforms state-of-the-art approaches regarding accuracy and runtime.

Abstract Real-world data of multi-class classification tasks often show complex data characteristics that lead to a reduced classification performance. Major analytical challenges are a high degree of multi-class imbalance within data and a heterogeneous feature space, which increases the number and complexity of class patterns. Existing solutions to classification or data pre-processing only address one of these two challenges in isolation. We propose a novel classification approach that explicitly addresses both challenges of multi-class imbalance and heterogeneous feature space together. As main contribution, this approach exploits domain knowledge in terms of a taxonomy to systematically prepare the training data. Based on an experimental evaluation on both real-world data and several synthetically generated data sets, we show that our approach outperforms any other classification technique in terms of accuracy. Furthermore, it entails considerable practical benefits in real-world use cases, e.g., it reduces rework required in the area of product quality control.

Abstract Clustering is a fundamental primitive in manifold applications. In order to achieve valuable results in exploratory clustering analyses, parameters of the clustering algorithm have to be set appropriately, which is a tremendous pitfall. We observe multiple challenges for large-scale exploration processes. On the one hand, they require specific methods to efficiently explore large parameter search spaces. On the other hand, they often exhibit large runtimes, in particular when large datasets are analyzed using clustering algorithms with super-polynomial runtimes, which repeatedly need to be executed within exploratory clustering analyses. We address these challenges as follows: First, we present LOG-Means and show that it provides estimates for the number of clusters in sublinear time regarding the defined search space, i.e., provably requiring less executions of a clustering algorithm than existing methods. Second, we demonstrate how to exploit fundamental characteristics of exploratory clustering analyses in order to significantly accelerate the (repetitive) execution of clustering algorithms on large datasets. Third, we show how these challenges can be tackled at the same time. To the best of our knowledge, this is the first work which simultaneously addresses the above-mentioned challenges. In our comprehensive evaluation, we unveil that our proposed methods significantly outperform state-of-the-art methods, thus especially supporting novice analysts for exploratory clustering analyses in large-scale exploration processes.

\n Data analysis is a highly iterative process. In order to achieve\n valuable analysis results, analysts typically execute many\n configurations, i.e., algorithms and their hyperparameter settings,\n based on their domain knowledge. While experienced analysts may be\n able to define small search spaces for promising configurations,\n especially novice analysts define large search spaces due to their\n lack of domain knowledge. In the worst case, they perform an\n exhaustive search throughout the whole search space, resulting in\n infeasible runtimes. Recent advances in the research area of AutoML\n address this challenge by supporting novice analysts in the combined\n algorithm selection and hyperparameter optimization (CASH) problem\n for supervised learning tasks. However, no such systems exist for\n unsupervised learning tasks, such as the prevalent task of\n clustering analysis. In this work, we present our novel AutoML4Clust\n approach, which efficiently supports novice analysts regarding CASH\n for clustering analyses. To the best of our knowledge, this is the\n first thoroughly elaborated approach in this area. Our comprehensive\n evaluation unveils that AutoML4Clust significantly outperforms\n several existing approaches, as it achieves considerable speedups\n for the CASH problem, while still achieving very valuable clustering\n results.\n

The plethora of available analytic platforms escalates the difficulty of selecting the most appropriate platform for a certain data mining task and datasets with varying characteristics. Especially novice analysts experience difficulties to keep up with the latest technical developments. In this demo, we present the ASAP-DM framework. ASAP-DM is able to automatically select a well-performing analytic platform for a given data mining task via an intuitive web interface, thus especially supporting novice analysts. The take-aways for demo attendees are: (1) a good understanding of the challenges of various data mining workloads, dataset characteristics, and the effects on the selection of analytic platforms, (2) useful insights on how ASAP-DM internally works, and (3) how to benefit from ASAP-DM for exploratory data analysis.

\n The Internet of Things is applied in many domains and collects vast\n amounts of data. This data provides access to a lot of knowledge\n when analyzed comprehensively. However, advanced analysis techniques\n such as predictive or prescriptive analytics require access to both,\n history data, i.e., long-term persisted data, and real-time data as\n well as a joint view on both types of data. State-of-the-art hybrid\n processing architectures for big data - namely, the Lambda and the\n Kappa Architecture - support the processing of history data and\n real-time data. However, they lack of a tight coupling of the two\n processing modes. That is, the user has to do a lot of work manually\n in order to enable a comprehensive analysis of the data. For\n instance, the user has to combine the results of both processing\n modes or apply knowledge from one processing mode to the other.\n Therefore, we introduce a novel hybrid processing architecture for\n big data, called BRAID. BRAID intertwines the processing of history\n data and real-time data by adding communication channels between the\n batch engine and the stream engine. This enables to carry out\n comprehensive analyses automatically at a reasonable overhead.\n

Scientific workflows have to deal with highly heterogeneous data environments. In particular, they have to carry out complex data provisioning tasks that filter and transform heterogeneous input data in such a way that underlying tools or services can ingest them. This results in a high complexity of workflow design. Scientists often want to design their workflows on their own, but usually do not have the necessary skills to cope with this complexity. Therefore, we have developed a pattern-based approach to workflow design, thereby mainly focusing on workflows that realize numeric simulations [4]. This approach removes the burden from scientists to specify low-level details of data provisioning. In this demonstration, we apply a prototype implementation of our approach to various use cases and show how it makes simulation workflow design tailor-made for scientists.

Scientific workflows often have to process huge data sets in a multiplicity of data formats. For that purpose, they typically embed complex data provisioning tasks that transform these heterogeneous data into formats the underlying tools or services can handle. This results in an increased complexity of workflow design. As scientists typically design their scientific workflows on their own, this complexity hinders them to concentrate on their core issue, namely the experiments, analyses, or simulations they conduct. In this paper, we present the core idea of a pattern-based approach to alleviate the design of scientific workflows. This approach is particularly targeted at the needs of scientists. We exemplify and assess the pattern-based design approach by applying it to a complex scientific workflow realizing a real-world simulation of structure changes in bones.

Workflow languages like BPEL are broadly adopted by industry to integrate the heterogeneous applications and data stores of an enterprise. Leading vendors provide extensions to BPEL that allow for a tight integration of data processing capabilities into the process logic. Business processes exploiting these capabilities show a remarkable potential for optimization. In this demonstration, we present PGM/F, a framework for the optimization of data processing in such business processes.

Over the last years, data management products as well as workflow products have established themselves as indispensable building blocks for advanced IT systems in almost all application areas. Recently, many vendors have created innovative product extensions that combine service-oriented frameworks with powerful workflow and data management capabilities. In this paper, we discuss several workflow products from different vendors with a specific focus on their SQL support. We provide a comparison based on a set of important data management patterns and illustrate the characteristics of various approaches by means of a running example.

No abstract available.

This paper presents a new approach for the development of data-intensive web applications that depend on sophisticated application logic. E-Commerce web sites, on-line auction systems and large enterprise web portals fall into this category as they require comprehensive data access, data processing and data manipulation capabilities. However, existing methodologies mainly concentrate on modeling content, navigation and presentation aspects of read-only web sites. In our opinion these models are not sufficient to express complex operations that access or modify web application content. Therefore, we propose an additional Operation Model defining the operation logic of a web application. We show that based on this model a significant part of a web application's Operation Layer can be generated, still allowing the manual implementation of arbitrary additional functionality. We evaluate our approach and present experimental results based on a large example application for the area of innovation management.

In enterprises, information is encoded in documents and databases. Logically, the information in both worlds is tightly connected, however, on the system level there is usually a large gap. In this paper, we propose a framework that improves document retrieval by exploiting available enterprise databases. In particular, we use database information to model the context of documents and incorporate this context in our search framework. We present our framework architecture, its components and its major interfaces. The framework can be configured and enhanced at well-defined points and, hence, can easily be customized to other domains. We furthermore evaluate its core components. Our experiments show that the context-aware approach significantly improves the quality of search results

Information in enterprises comes in documents and data bases. From a semantic viewpoint, both kinds of information are usually tightly connected. In this paper, we propose to enhance common search-engines with contextual information retrieved from databases. We establish system requirements and anecdotally demonstrate how documents and database information can be represented as the nodes of a graph. Then, we give an example how we exploit this graph information for document retrieval.

Many decision support applications are built upon data mining and OLAP tools and allow users to answer information requests based on a data warehouse that is managed by a powerful DBMS. We focus on tools that generate sequences of SQL statements in order to produce the requested information. Our thorough analysis revealed that many sequences of queries that are generated by commercial tools are not very efficient. An optimized system architecture is suggested for these applications. The main component is a DSS optimizer that accepts previously generated sequences of queries and remodels them according to a set of optimization strategies, before they are executed by the underlying database system. The advantages of this extended architecture are discussed and a couple of appropriate optimization strategies are identified. Experimental results are given, showing that these strategies are appropriate to optimize query sequences of OLAP applications.