Umeshwar Dayal

Report on the Seventh International Workshop on Business Intelligence for the Real Time Enterprise (BIRTE 2013)

This paper reports on the 7th International Workshop on Business Intelligence for the Real Time Enterprise (BIRTE 2013), co-located with the VLDB 2013 conference. The BIRTE workshop series aims at providing a forum for presentation of the latest research results, new technology developments, and new applications in the areas of business intelligence and real time enterprises. Building on the success of the previous BIRTE workshops, co-located with the VLDB conferences in Seoul, Auckland, Lyon, Singapore, Seattle, and Istanbul, the seventh workshop in the series was held in Riva del Garda, Italy, on August 26, 2013. Today, business analytics have to use new data sources and technologies in order for the business to be completely up-to-date. Traditional “in-house” data sources about transactions, sales, and finances still form the cornerstone of business analytics applications, but this is no longer enough. Instead, “Big Data” with high velocity such as tweets and other social network updates and sensor data from RFID, GPS, Bluetooth, etc. must be captured and analyzed instantly to understand the latest customer and market trends. Further, analyzing the past and even the present is no longer enough, so predictive analytics solutions are used to make decisions based on the expected future. These new applications and data sources mean that existing business intelligence methods and techniques must be revisited to provide better e ciency, scalability, expressiveness, and ease-of-use. BIRTE 2013 featured an exciting technical program including two keynotes, an invited industrial talk, a panel, and a number of peer-reviewed papers from di↵erent countries in Europe, Africa, and Asia. Each submission received three reviews from the members of the distinguished program committee consisting of leading researchers in the field from academia and industry. From these submissions, two full research papers and one short position paper, along with two demo papers, were selected for presentation at the conference. Based on the feedback of the reviewers and the feedback at the workshop, the authors have made revised versions of their papers which will be published in a joint post-proceedings volume of BIRTE 2013 and 2014 in the Springer LNBIB series [1]. BIRTE 2013 was extremely well attended, with a peak audience of over 70 persons.

An Approach to Benchmarking Industrial Big Data Applications

Through the increasing use of interconnected sensors, instrumentation, and smart machines, and the proliferation of social media and other open data, industrial operations and physical systems are generating ever increasing volumes of data of many different types. At the same time, advances in computing, storage, communication, and big data technologies are making it possible to collect, store, process, analyze and visualize enormous volumes of data at scale and at speed. The convergence of Operations Technology (OT) and Information Technology (IT), powered by innovative data analytics, holds the promise of using insights derived from these rich types of data to better manage our systems, resources, environment, health, social infrastructure, and industrial operations. Opportunities to apply innovative analytics abound in many industries (e.g., manufacturing, power distribution, oil and gas exploration and production, telecommunication, healthcare, agriculture, mining) and similarly in government (e.g., homeland security, smart cities, public transportation, accountable care). In developing several such applications over the years, we have come to realize that existing benchmarks for decision support, streaming data, event processing, or distributed processing are not adequate for industrial big data applications. One primary reason being that these benchmarks individually address narrow range of data and analytics processing needs of industrial big data applications. In this paper, we outline an approach we are taking to defining a benchmark that is motivated by typical industrial operations scenarios. We describe the main issues we are considering for the benchmark, including the typical data and processing requirements; representative queries and analytics operations over streaming and stored, structured and unstructured data; and the proposed simulator data architecture.