Category: Audit Selection

We interrupt our current blog series to share a recent interview with you. The key leaders at XDS (Joseph Hammond and James Brenza) were interviewed by Maureen Metcalf on her Voice America program titled “Innovative Leaders Driving Thriving Organizations”. Maureen’s weekly program features interviews of thought leaders, academics and executives to identify their biggest issues, and discuss the innovative approaches they are using to turn turbulence into a business advantage.

XDS has built some highly advanced algorithms into their audit selection product. Their state-of-the-art solution utilizes automated machine learning to develop and tune models to identify tax fraud that is unique to your state. In the broadcast, Maureen dives into why XDS pushed the envelope so far and how our customers can shift their thinking to similarly advance their organizations.

While the entire broadcast is loaded with valuable nuggets, you may be especially interested in some of these discussions at the mm:ss time marks noted below:

• What are the major technology trends that are making analytics easier? (@ 4:40)
• What challenges remain for analytics programs? (@ 9:00)
• What’s the general nature of XDS’ analytic product? (@ 21:45)
• Since progress is hindered by teams that are “stuck”, how do we recommend teams get “unstuck”? (@ 26:00)
• How does our product benefit the public? (@ 26:40)
• How does our focus on being fair and equitable benefit everybody? (@ 27:15)
• How can you get your leadership aligned on identifying the non-compliant 1% of the population more effectively? (@ 31:00)
• How do business agility and analytics work together? (@ 34:35)
• As a leader, how do you create an environment that enables team success? (@ 42:20)

As with all of XDS’ solutions, the process and organization elements are balanced with amazing technology. So while this broadcast sounds extremely technical, we’re certain you’ll find some key answers to how your organization can move forward regardless of the number of technology hurdles.

We look forward to returning you to our regularly schedule blogs next week. Rather than discuss these challenges, we’d rather help you overcome them. You can find our contact information here to schedule design your implementation plan.

In our prior audit selection blog posts, we discussed the significance and benefits of data-driven audit selection. In our most recent post, we discussed the nuances of data management and the art of data science. We are confident that these will create major departures from how you have traditionally approached audit selection.

To help you realize a more productive future, we are going to turn our attention to change leadership. To enact change, one of the first critical phases is creating a climate for change. While we may just want to ignore the individuals that fall back on the excuse “we have always done it this way,” ignoring the negativity is not an effective way of leading change. One of the first steps is to create a sense of urgency based on the importance of finding new methods to boost compliance. That sense of urgency can be based on the rapid increase in fraud techniques that you are not discovering actively. The second step is to create a powerful coalition with people that are aligned with that perspective. While there is strength in numbers, there is more strength with key influencers. With a small cadre of proactive supporters, you can collectively create a vision for change. You will have a significant advantage if they help create that vision. They will have a sense of ownership to help move it forward within their circle of influence.

The next critical phase is engaging and enabling the organization. This is the time to get more of the organization involved. The first step in this phase is to communicate the vision. If you have your powerful coalition prepared, they will help you convey the vision through a variety of channels (e.g., team meetings, posters, newsletter, etc.). You need to be prepared to do more than just talk about it – you need to be prepared to empower action throughout the team. It is critical to remember that you are leading the change. This means you do not need to execute every action personally. However, you can help the team create quick wins. Even though they may be small steps, any step forward needs to be recognized and celebrated.

The last phase capitalizes on momentum to build more momentum. This is the phase where you are implementing and sustaining change. In this phase, the first step is to build on the changes that have been successful. Each small victory is critical to build toward the next victory. To use the old saying, “Rome wasn’t built in a day.” Your coalition needs to be prepared to provide continuous support to maintain progress. This will allow you to help make change stick. For many organizations, it will take at least one year to make the new way the way you do all of our work. You will get there with patience and perseverance.

XDS believes the biggest success factor is trying a series of small, controlled experiments delivered as proofs-of-concept for acceptance and momentum. These will help you contain risks and raise awareness of your quick wins. If you are having problems demonstrating your first success in 90 days, you may want to call us. We have the ability to leap over barriers and deliver rapid results.

The journey to being data-driven

While it is easy to talk about transitioning to a data-driven audit selection process, it can be a difficult transformation. It is beyond a technology change. It requires process changes as well as organization changes. We will address some of those challenges in future posts. In this post, we will focus on the technological aspects of this transformation.

One of the first aspects is data governance. While it is not an exciting topic, it is the foundation of a data-driven process. Analytics are most effective when performed on trusted data. We like to jokingly refer to this process as “land it, scrub it, and trust it.” Prior to turning your data scientist loose on the data, it is vital to get your data sources identified, organized, defined, profiled, and controlled. Here we briefly explain each aspect:

• Identify – Name specific business domains of critical data and where it is stored.
• Organize – Isolate the location of every needed data source and how it will integrate with other data sources.
• Define – Prepare a business description of every attribute to ensure your team understands what it is and how it will relate to their analytic objectives.
• Profile – Document the specific values, or ranges, of values to ensure they are aligned with your definitions.
• Control – Based on definitions and profiles, create quality rules that will be assessed with every refresh of the data. This will ensure it remains aligned with your expectations and needs.

Data governance is not a one-time event or a barrier for initiating your transformation. You can start with a minimal number of data sources and qualify them incrementally. Starting with something is more valuable than starting nothing while you wait for perfection.

We frequently receive questions on the amount of historical data necessary. While results can be produced with limited amounts of historical data, accuracy improves as more data is made available. There is not a firm definition of the amount necessary, however a few years of data will establish an analytic baseline. Ideally, this means having a few years of aligned history.  “Aligned history” means the data sources must match in the same time period. For example, attempting to correlate 2008 audit outcomes with 2014 tax forms is not a useful combination.

The significance of external data cannot be over emphasized. If your team only uses data from your tax forms and IRS data sets, you are only getting a small portion of the complete picture. To have robust models, you should incorporate data from multiple state sources (e.g., business and vendor licenses), vehicle registrations, and external data sources (e.g., third party published business listings). In addition to providing discovery leads, this additional data will provide a more complete view of your taxpayers.

The Art of Data Science

Data science is the application of statistical analysis to large volumes of data. While driven by science, there is also an “art” to the techniques and methods. From a technical perspective, your team and their tools must be prepared to incorporate these modeling methods:

• Discriminant, generalized linear, logistic and nonparametric regression models
• Decision trees
• Neural networks
• K-means clustering

With the wide variety of science behind just those few model types, you can start to see the need for the “art,” or the experiential side of data science. The experiential aspect to selecting the correct model type for your data is highly dependent on what data is available and may change with refreshed data sets. The best model for your situation may be a blend of different, underlying models. This is very similar to a weather forecast model consisting of a mix of over 100 individual models rather than just one “golden” model. While finding the optimal model requires extensive mathematics and statistics, it also requires a significant amount of “art” to be successful.

One of the final challenges with applying data science is incorporating automation. Due to the extensive libraries of modeling methods, a state-of-the-art solution requires automation to support the data scientist. This will enable them to adapt to various data sets and quickly deliver results. Additionally, as data sets and fraudulent practices shift, revision of models requires automation. The volume and complexity of the methods dictates automation to maintain the pace of change.

XDS doesn’t just talk about the challenges and opportunities. We exist to help you rapidly realize the future. Turning the corner toward a data-driven and productive approach can be a significant initiative. To discover some key steps to gaining executive support for your transformation, return for our next post in the series: Build Executive Support for Progress.

The critical role of auditing
Attaining and maintaining compliant taxpayers is the core of your job. However, that does not mean it is easy. States rely on voluntary compliance with tax laws to fund state government and assist local government. Maintaining a high level of voluntary compliance requires some checks and balances. In some cases, enforcement efforts need to be audits. Audits are the most effective compliance tool available to state agencies. However, audits are lengthy and expensive. When combined with staffing levels controlled by tighter and tighter budgets, agency leaders must look for efficiencies to maximize all that they do – including auditor’s efforts.

Determining who to audit is one of the most challenging efforts in the audit process. Your auditors are faced with an unbelievably large population of audit opportunities. The problem is that a huge percentage of the population is compliant, which is a good problem to have. The probability of a false positive (i.e., selecting and auditing a company that is compliant) is non-productive, frustrates the taxpayers, and can trigger an avalanche of negative feedback from taxpayers, administrators and political leaders.

Identifying the least compliant taxpayer from the millions of compliant tax payers is not a simple task. Answers to the question of “who is the least compliant taxpayer” may vary, depending on who you ask. Is it the fraudulent taxpayer? The taxpayer that owes the most? Is auditing a trust tax a factor? Are specific industries or geographic locations more problematic? The answer can shift or be a combination of various elements. Using large amounts of data and the right resources to identify all scenarios creates an effective and very flexible model for audit selection.
Many states have auditors located in district or regional offices, telecommuting and out-of-state offices. Some states have assigned the audit selection task to these geographically distributed teams or individual auditors. Some states have their auditors and regional offices focus on their local geography which translates to local businesses being audited. This may make it easier to monitor persistent offenders that are in their immediate area and reduce the time and cost of travel.

Unfortunately, this approach also has some significant shortcomings. The first is the inability to objectively defend being fair and equitable audit selections. Without substantiating data, it’s difficult to overcome objections of targeting or discrimination. With the small percentage of non-compliant businesses, it is extremely hard to maintain the appropriate focus on the larger geographic area and many mid-tier businesses that avoid detection. While many auditors and managers have extensive skills and training in specific taxes, finding non-compliant businesses may not be their strength.

The benefits of effective audit selection

Effective audit selection can deliver amazing results to your department. While technology advances are available, and some may be already in-place, utilizing state-of-the art technologies and services will rapidly increase the number of productive audits and minimize the false positives. Your team can experience a much higher hourly productivity if they are receiving qualified leads. Rather than spend time searching for audit leads, they can go straight to the source detail and quantify their audit lead more rapidly and accurately. For example, here are some results from a large mid-west state:

• 80% reduction in unproductive audits
• Over 30,000 hours of auditor time saved in identifying audit leads
• Productivity gain resulting in over $33m revenue per year
• Discovery of a new audit program that resulted in over $5.5m in collections within the first six months
• Taxpayer base subject to audit reduced from millions to a few thousand

The results from a data-driven model enable fair and equitable identification, and distribution of audit leads across all tax types, industries, and geographical locations, with a strong focus on the least compliant taxpayer.

XDS realizes that it can be very difficult to move to data-driven audit selection. We exist to help you realize that transition quickly and easily. To get into more details on the art of data science, return for our next post in the series: Pivoting to Data-Driven Audit Selection.