Published on 16-Jan-2013
"The business analytics competency center has enabled us to take a more strategic approach to analytics, and we want to share our knowledge with other USDA agencies. Ultimately, we are hoping to be able to offer a cloud analytics service that can be harnessed by other USDA agencies that want to use it." - Todd Schroeder, Director of Business Systems, APHIS
BA - Business Analytics, BA - Business Intelligence, BA - Performance Management, BA - Predictive Analytics, Big Data & Analytics, Big Data & Analytics: Operations/Fraud/Threats, Business Integration, Business Performance Transformation
The Animal and Plant Health Inspection Services (APHIS) is an agency within the United States Department of Agriculture (USDA) that focuses on safeguarding US agriculture against the threat of pests and diseases. The agency inspects imported agricultural products at the point of entry, certify US exports to make sure they meet the appropriate standards, and monitor and control the movement of crops, livestock and soil between states. When an outbreak of pests or a disease epidemic is identified, the agency is responsible for organizing quarantine.
To identify ways to enhance and streamline its inspection processes and improve animal and plant health management, APHIS needed better insight across all its operational systems and data.
APHIS decided to standardize on a single analytics platform, built around a suite of IBM Business Analytics software. The solution can automatically generate inspection certificates for product shipments and send various notifications related to operational activities at ports as well as throughout domestic programs. The agency is also investigating the use of predictive modeling to improve inspection efficiency.
Automating the emergency action notification reporting has enabled APHIS to redeploy one full-time analyst into a more valuable role. Replacing duplicative reporting tools with a single analytics solution has reduced costs by 30 percent.
Fact-based decision-making enables APHIS to increase efficiency and improve service levels while operating within a strictly limited budget. Predictive analytics has the potential to improve inspection hit-rates by identifying high-risk shipments.
The Animal and Plant Health Inspection Services (APHIS) is an agency within the United States Department of Agriculture (USDA) that focuses on safeguarding US agriculture against the threat of pests and diseases. The agency inspects imported agricultural products at the point of entry, certify US exports to make sure they meet the appropriate standards, and monitor and control the movement of crops, livestock and soil between states. When an outbreak of pests or a disease epidemic is identified, the agency is responsible for organizing quarantine and executing plans to contain and mitigate the risk.
Taking a smarter approach
Todd Schroeder, Director of Business Systems at APHIS, comments: “Our responsibilities are broad, our work is specialized and multifaceted, and we deal with tens of thousands of agricultural inspections every week. We use about 26 different systems to manage all the different aspects of our business, and these systems collect and process large volumes of data.
“We realized that in the long term, unlocking the potential of this data will be the key to providing an effective service. If we can gain a better understanding of exactly which pests are likely to be imported from which countries at which times of year, or predict the regions where disease outbreaks are most likely, we should be able to focus our efforts on the highest-risk areas and significantly improve the hit-rate for inspections.
“The job gets bigger all the time, but we operate in an economic climate where there is constant pressure on public finances. If we want to maintain and improve the level of protection we can offer to the nation’s agriculture, we can’t just hire more inspectors to inspect everything. We need to work smarter.”
The need for a single analytics platform
APHIS was using a number of different reporting tools to extract data from its systems, and it was almost impossible to get a coherent view across the whole agency’s operations or “join the dots” to identify patterns and trends in disease or pest epidemics. The tools were also costly to maintain, in terms of both software licensing and finding staff with the skills required to utilize them effectively.
“As a first step, we needed to standardize on a single reporting platform, and we selected a suite of IBM Business Analytics software,” says Todd Schroeder. “We started out with IBM Cognos® Business Intelligence for operational reporting, and we’re now developing our use of IBM Cognos TM1® for financial management and IBM SPSS® Modeler for more advanced analytics and predictive modeling.”
By replacing many duplicative reporting tools with a single solution, APHIS has been able to reduce the cost of its analytics capabilities by 30 percent.
Moreover, by substantially improving and streamlining the agency’s operational reporting processes, the new solution provides significant year-on-year benefits. By reducing the need for APHIS’s analysts and other staff to manually gather, process, format and distribute data, it allows them to focus on more valuable tasks.
Automating operational reporting
When farmers wants to export their produce, they can log in to the USDA website and apply for an export certificate. This triggers an inspection of their farm and the commodity they are exporting. If the farmer passes the inspection, the USDA system issues a certificate that they can print and attach to the shipment.
These certificates describe the point of origin, the commodity being exported, the treatments to which it has been subjected, and the destinations to which it is allowed to be shipped. APHIS uses its IBM Cognos Business Intelligence solution to fully automate the certificate generation process: extracting the relevant data from its source systems, outputting it in a standard certificate format, and making it available for the farmer to print. Over 30,000 of these certificates are issued every week, and without an automated solution, APHIS would struggle to cope with the administrative workload.
Regulated agricultural produce imported to the United States requires inspection at the point of entry, to ensure that pests and diseases are not brought into the country. If a shipment is inspected and problems are found, APHIS issues an emergency action notification (EAN). This is a report that describes the inspection and instructs the owner of the shipment and the regulators about the proper handling procedure for the release of the produce. It also specifies the actions that need to be taken to mitigate the problem – for example, applying a treatment to kill off the pests or diseases that have been detected, or re-exporting or destroying the produce.
Copies of the EANs need to be sent out to the relevant authorities in each state, and to various other recipients, depending on the type of produce, the port of entry and the location of the shipments. There are over 350 possible recipients for each EAN, and making sure that the right EANs were being sent to the right people used to be a full-time job for one of APHIS’s analysts. Now, the Cognos solution handles the whole process automatically, generating and sending every EAN to the appropriate recipients based on predefined criteria.
Movement of soil, crops and livestock
If a herd of cows develops foot and mouth disease or a vineyard becomes infested with European grapevine moths, for example, APHIS is responsible for imposing appropriate quarantine zones in the affected counties. Inter-state transportation of affected animals, crops and soil is prohibited, and appropriate action is coordinated to eradicate the problem.
Cognos helps APHIS run these operations by making timely information available to regulatory inspectors to ensure regulations are followed and quarantine boundaries are effective. The solution also helps to manage the inspection process associated with continuing movement of agricultural products out of regulated areas.
Gaining deeper insights
“As we continue to develop our analytics environment and build up a historical record of import, export and domestic inspection data, we’re beginning to look at the data from a more strategic point of view,” comments Todd Schroeder. “For example, we could look at imports in a given month for the past few years, and see what kinds of pests and diseases we most commonly detect at that time of year, and what kinds of shipment are most likely to be at risk of infection.”
“IBM SPSS Modeler gives us the ability to perform this kind of advanced statistical analysis, and we are currently working with IBM to decide which areas of our operations are likely to benefit the most from predictive analytics. Ultimately we’re planning to put together a prioritized list of research projects, and start putting this technology into practice.”
Acting as a cloud analytics provider
The APHIS analytics platform has gained attention from other agencies within the USDA, and the APHIS team is now looking at methods of replicating their success across the department.
“We started out by using Cognos to analyze data from one of our databases, and then gradually added other data sources until all of our major systems were part of the solution,” explains Todd Schroeder. “As we developed the solution, we learned a lot, not only about the technical aspects and data structures, but also about the governance of analytics within our organization.
“As the complexity of the analytics environment increases, centralized management becomes more and more crucial, so we are in the process of founding a business analytics competency center [BACC] that works in parallel with our IT team. This has enabled us to take a more strategic approach to analytics, and we want to share our knowledge with other USDA agencies. Ultimately, we are hoping to be able to offer a cloud analytics service that can be harnessed by other USDA agencies that want to use it.”
He concludes: “From our point of view, in the light of economic pressures, making more profitable use of operational data is absolutely vital to our ability to operate in a more effective and efficient way. Our efforts to enhance our analytics capabilities and enable evidence-based decision-making are allowing APHIS to maintain and improve its service levels with fewer resources and tighter budgets.”
About IBM Business Analytics
IBM Business Analytics software delivers data-driven insights that help organizations work smarter and outperform their peers. This comprehensive portfolio includes solutions for business intelligence, predictive analytics and decision management, performance management, and risk management.
Business Analytics solutions enable companies to identify and visualize trends and patterns in areas, such as customer analytics, that can have a profound effect on business performance. They can compare scenarios, anticipate potential threats and opportunities, better plan, budget and forecast resources, balance risks against expected returns and work to meet regulatory requirements. By making analytics widely available, organizations can align tactical and strategic decision-making to achieve business goals.
For more information
For further information please visit ibm.com/business-analytics
Products and services used
© Copyright IBM Corporation 2013. IBM Corporation, Software Group, Route 100, Somers, NY 10589. Produced in the United States of America. January 2013. IBM, the IBM logo, ibm.com, Cognos, SPSS and TM1 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 www.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. The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the client is in compliance with any law or regulation.