DERTour provides search for hotel, flight, and other travel offers, using massive data sets. Over 250 million hotel offers, for example, are searched by several independent filter parameters, and the offers are updated several times per day. With ParStream’s continuous import of new offers, high throughput on small infrastructure, and sub-second response times, DERTour is able to provide their customers with the right travel offers instantly.
ParStream’s ability to provide real-time responses on big data queries while simultaneously absorbing on-the-fly clickstreams at rates of over 100,000 per second has allowed etracker to develop an innovative in-depth interactive analytics service including live-segmentation. With a performance boost ranging from 500 to 12,000 times faster than their previous MySQL based solution, not only are they now able to serve high resolution (to the individual click) results over an extended period, they’re also able to fulfill the service with a substantially lower cost infrastructure.
ParStream is the analytics platform for Searchmetrics, a search and social analytics software company that monitors over 75 million domains and 100 million keywords on the worlds biggest search engines.
Searchmetrics customers use the service to monitor competing domains and to optimize their keywords to drive traffic. This translates into typical imports of over seven terabytes of data and querying more than ten billion data records. By switching to ParStream, Searchmetrics greatly reduced infrastructure requirement and achieved faster import and query execution times.
The ParStream Real-Time Database was selected by bd4travel to power real-time analytics for the travel industry, delivering insights fast enough to operate in the dynamic travel market. bd4travel specializes in data analytics and real time business intelligence solutions for the travel industry. The bd4travel data management platform utilizes ParStream and supports online portals and tour operators to better understand their audience and to accommodate each potential traveller in real time with the best answers and recommendations to their individual concerns – before, during or after their trip, using mobile, web or social media channels.
Customer provides a highly scalable enterprise SaaS tracking platform providing business intelligence to performance-based marketers. Their SaaS offering helps performance marketers a way to tie their measurable ROI back to to their digital spend to better optimize the performance of their marketing campaigns and ad investments. It collects click-forward data including conversion information, landing page data, impression traffic for display campaigns, ecommerce orders on the backside and ties that ROI back to the publisher it came from. By implementing ParStream, customer will be able to run new reports, specifically better ways of attribution (or the path of the consumer and how it relates to the cost and value of each touch point on that customers journey).
Ellisphere, previously known under the name Coface Services, is the reference in business information services in France. Their Data Solutions business unit offers B2B data and data services via a web-based application (SaaS) or through APIs for CRM integration. Composed of 15 billion+ data points forming the most extensive collection of business information in France, Ellisphere delivers the best in breed BI application. Ellisphere chose ParStream over other database vendors to power their faceted search solution. ParStream was chosen for the real-time performance, the scalability on large data, the ability to run on standard hardware, and the fact that no specialized training was needed.
Telecommunications companies require real-time analytics on the big data to ensure not only that the networks they are managing are running at maximum efficiency, but also to generate new revenue streams from these valuable data sources . Much of the data is captured at the edge of the network, so the volume, diversity, and speed of the data causes difficulties when making decisions based on real-time analysis. The ParStream Real-Time Database reduces network overhead and improves query speed by enabling in-line analytics of the data at the remote nodes themselves. The instances run independently of each other and can be queried directly; processing and analytics of 100% of the data happens at the remote nodes. This telecommunications company uses ParStream to search for network anomalies and inefficiencies, and to perform complex analysis of raw flow records in real-time.
MPREIS is a large Austrian retail chain with 219 markets and 158 Bistros. The company has been using QlikView extensively over the past three years for sales and other business analytics for all of the MPREIS sites. With the introduction of the Direct Discovery feature in the current QlikView release, ParStream and QlikView were able to combine In-Memory data analysis from QlikView with On-Demand data analysis from ParStream for MPREIS. The two technologies, the QlikView in-memory engine and ParStream Real-Time Database, are complementary since they perform well in different situations. In a showcase 6 billion rows of transactional, daily sales data for retail stores were generated in order to proof performance. Due to the very promising results ParStream has been selected as underlying data store for detailed POS analysis.
INRA coordinates and hosts MetaGenoPolis (MGP), a unique facility in Europe at the service of the medical, scientific and industrial communities. Under the direction of Stanislav Dusko Ehrlich, a world expert in microbiology and a pioneer of metagenomics, the MGP team has established recognized scientific landmarks. Their research paves the way for early diagnosis and new therapies for many diseases such as diabetes, obesity and metabolic diseases generally associated with our digestive system. The research pipeline requires ultra-high throughput/data import rates and yet it also requires Interactive data analytics, such as the capacity to filter, select and perform sub-second aggregations on data within a peta-scale data store. ParStream was chosen for the performance and flexibility.
German Climate Research Institute
ParStream is used to support real-time monitoring of one of the most – if not the most – complex system in the world: The climate. ParStream was selected by the German Climate Research Center in Hamburg to support their predictive analytical efforts in early detection of hurricanes.
Two analytical capabilities are essential for hurricane detection- Massive, multi-dimensional filtering and fast geo-clustering. Before ParStream, it took the Center several hours to analyze the simulation results. The dangers were enormous, since people’s lives and livelihoods were at risk.
ParStream now supports a multi-dimensional filter operation on three billion data records while geo-clustering the resulting 100,000 records in less than one second. The result is a massive improvement in the pre-warning time for evolving hurricanes.
German Ministry of Economics
The German-language Web, with currently more than six billion web pages, provides extraordinary potential for numerous applications, for example in the areas of market and trend research, distribution of messages in speech processing, and generally in the “business intelligence” area. The project “MIA – a marketplace of information and analysis”, funded by the Federal Ministry of Economics under the “Trusted Cloud” Competition and developed by a consortium of industrial and research partners under the leadership of the Department of Database Systems and Information Management (DIMA) of the Technical University of Berlin, developed an information marketplace for Germany. ParStream is selected as a partner for this initiative to extract structured information from the German Internet and store in a central location, to provide a database service for all commercial and non-commercial organizations. ParStream became a member of the Trusted Cloud initiative.
Geospatial applications are huge in size and usually consist of billions of floating point values resulting from measurements, seismic analytics and advanced simulation. Geologists typically search in an interactive process for certain combinations of values to identify “hot” areas.
As the capacity to collect geological and seismic data-points increases, so do the requirements for measurement analytics and real-time/interactive responses by researchers. This international mining company used ParStream to perform interactive, investigative and multi-dimensional analytics, reducing query response from 10 minutes to less than 1 second.
A global manufacturing company is using ParStream to store and analyze sensor measurements. Over 2000 sensors per device capture temperature, pressure, vibration, and other measurements, generated at a frequency of up to 20 readings per second. The system is used to optimize the design and runtime behavior of the units, searching for comment patterns that appear in specific trouble or out-of-band scenarios. The results will be used for a solution to improve their products and internal processes.