Petrol dramatically decreases analytics query times

An IBM appliance accelerates complex queries, delivering point-of-sale suggest-sell insights

Published on 18-Jul-2013

"IBM provides us with tools that align with smarter commerce, enabling us to deliver the right message to the right person at the right time, to understand product affinities and intelligently drive the sale, all in a customer-centric way." - Mr. Pavel Batista, chief information officer, Petrol d.d.

Customer:
Petrol d.d.

Industry:
Retail, Chemicals & Petroleum

Deployment country:
Slovenia

Solution:
BA - Business Analytics, BA - Business Intelligence, BA - Predictive Analytics, Big Data & Analytics, Big Data & Analytics: Customers, Business Integration, Business Performance Transformation, Smarter Commerce, System z Software

Overview

Petrol d.d. is the principal strategic supplier of oil and other energy products for the Slovenian market. Through approximately 570 service stations, Petrol offers a broad range of automotive goods and services and a wide selection of household items, food products and other merchandise.

Business need:
Petrol d.d. wanted to use historical and transactional data from its retail stores to improve sales, but its analytics environment could not manage the required query volumes or complexity.

Solution:
With an IBM® DB2® Analytics Accelerator for z/OS® appliance boosting IBM Cognos® software query performance, Petrol store employees access product sales data to more effectively suggest-sell at the point of sale.

Benefits:
Petrol accelerates its analytics queries and increases retail sales.

Case Study

Petrol d.d. is the principal strategic supplier of oil and other energy products for the Slovenian market. Through approximately 570 service stations, Petrol offers a broad range of automotive goods and services and a wide selection of household items, food products and other merchandise.

Optimizing the analytics query environment

Collecting data and putting it to use are two distinct pursuits. Petrol had accumulated a significant amount of historical and transactional information from its retail stores and service stations, as well as its home oil and gas businesses. With its existing analytics processes, however, the company found it challenging to analyze that data and subsequently transform it into actionable, timely intelligence.

“We had very, very detailed data about product sales and about each individual customer in our loyalty program. These loyalty members not only shop at our stores, but they buy their home energy products and vehicles’ fuel from Petrol as well. Our goal at retail was to deliver, to the cashier at the store, the information they would need to suggest-sell specific products to those loyalty customers, as well as walk-in customers at the point of sale, in seconds,” says Pavel Batista, chief information officer for Petrol. “And keep in mind, this type of transaction happens two or three hundred thousand times per day across all our stores.”

Accelerating transaction-based and aggregate queries

Petrol analysts simply could not meet such a high-volume and high-speed demand for actionable intelligence. “It was not a sustainable model,” says Batista. With an expanding database that was already nearly 20 TB, queries were continually slowing while the desire for deep analysis was increasing.

To speed and automate its Cognos business intelligence software's data-mining capabilities, as well as to ensure reliability and data security, Petrol deployed the IBM DB2 Analytics Accelerator for z/OS appliance on an IBM zEnterprise 196 server platform. Approximately six months after this deployment, Petrol implemented IBM SPSS Modeler software, adding another dimension to the intelligence it sought regarding customer purchasing behaviors and product sales.

Beyond accelerating transaction-based, single-record business analytics queries to analyze and predict individual customer behavior, Petrol also began using the DB2 Analytics Accelerator appliance for aggregate queries, which provide company purchasing managers, marketers and merchandisers with product- and brand-level, geographically focused sales trends.

Aligning processes with smarter commerce

For Petrol, these new capabilities are critical to a smarter commerce initiative, which focuses on applying intelligence at the operational level and developing a new, more sophisticated dynamic between Petrol and its retail customers. Batista sees the implications of smarter commerce reaching far beyond suggest-selling at the point of sale to providing an optimal product mix at each Petrol store and individualizing the company’s presales messaging to the greatest extent possible.

“Smarter commerce is about transforming near-real-time analytics into personalized messages and offers for our customers. It’s a system that ensures that we’re not suggest-selling something the customer doesn’t want to buy; we’re offering him something he probably wants anyway, but he hasn’t thought about it,” says Batista, who explains that Petrol has been practicing suggest-selling for some time, though it has been based more on employee experience and judgment than on hard data. “IBM provides us with tools that align with smarter commerce, enabling us to deliver the right message to the right person at the right time, to understand product affinities and intelligently drive the sale, all in a customer-centric way.”

Reduced query times help increase sales

Batista credits this accelerated analytics platform, with the DB2 Analytics Accelerator appliance dramatically reducing query times, as playing a leading role in increasing sales. “The store employee enters what the customer is purchasing, and with the DB2 Analytics Accelerator appliance, the business analytics tools deliver information on complementary products in seconds. If the customer is a loyalty customer, the employee can see what he’s purchased in the past and make decisions on what other products to suggest at the point of customer contact. Everything is done on the customer’s timetable, in seconds, which keeps him satisfied with his shopping experience.”

For more information

To learn more about IBM Cognos or IBM SPSS software or the IBM DB2 Analytics Accelerator appliance, please contact your IBM representative or IBM Business Partner, or visit the following website: ibm.com/software/systemz

Additionally, IBM Global Financing can help you acquire the software capabilities that your business needs in the most cost-effective and strategic way possible. We'll partner with credit-qualified clients to customize a financing solution to suit your business and development goals, enable effective cash management, and improve your total cost of ownership. Fund your critical IT investment and propel your business forward with IBM Global Financing. For more information, visit: ibm.com/financing

Products and services used

IBM products and services that were used in this case study.

Hardware:
System z: zEnterprise 196 (z196)

Software:
DB2 Analytics Accelerator for z/OS, SPSS Modeler

Legal Information

© Copyright IBM Corporation 2013 IBM Corporation Software Group Route 100 Somers, NY 10589 Produced in the United States of America April 2013 IBM, the IBM logo, ibm.com, Cognos, DB2, and SPSS are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at ibm.com/legal/copytrade.shtml This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. The client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. It is the user’s responsibility to evaluate and verify the operation of any other products or programs with IBM products and programs. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.