Using AI to Power Prosperity During Tax Season

Sponsored by Intuit

By Ashok N. Srivastava, SVP & CDO, Intuit

Not many of us realize that 44 percent of people cannot come up with $400 for an emergency(1). Or that approximately 50 percent of new businesses fail within the first five years(2).

Artificial intelligence has been discussed in the technology industry for a long time. However, at Intuit, artificial intelligence is more than the latest buzzword — it is a key technology that can truly change customers’ lives. I believe that Intuit is in a unique position to help with our customers’ financial lives through artificial intelligence, because of the unrivaled set of financial and compliance data we can access.

Intuit began its artificial intelligence journey over 10 years ago and continues to use unique financial data, customer-focused innovation and machine learning to lessen the pain of managing finances for 46 million customers worldwide.

For most people, doing their taxes is one of the biggest financial transactions of the year, and also one of the most complicated. This can cause anxiety, as well as a lack of confidence that they are filing their taxes correctly and getting all the money they deserve.

At Intuit, we continue to bring our AI and machine learning expertise to the tax preparation experience. This started with building and using our own knowledge engine, which has been available to customers since tax-year 2014.

Through machine learning and artificial intelligence, we can learn from millions of customers what are the useful patterns and challenges in taxes.

For example, if you are a florist, we could look at every other florist who has filed with TurboTax, evaluate the deductions used by these virtual peers, and then recommend appropriate approaches for your taxes. You could just say yes or no verbally to these suggestions, and then we could get it done. That’s our vision.

Today, TurboTax uses artificial intelligence to help customers get their maximum refund by recommending whether to go through the time-intensive itemized deduction process or not. This can save users up to 40 percent of tax prep time and significant document retrieval effort. And, for those who do itemize, TurboTax uses data analysis and machine learning to identify and recommend deductions, including obscure ones.

We also apply artificial intelligence technology to product development, to speed up the development process of getting our tax software to market each year with the latest tax codes and maximum accuracy. Artificial intelligence and machine learning allow us to convert the massive and complex 80,000 pages of the U.S. Federal tax code into an application that simplifies the process for our customers.

We created a a tax knowledge engine (TKE) which encodes large amounts of conditionally-related tax constraints into tax knowledge graphs. The engine can then intelligently handle the many different types of tax situations faced by consumers.

Similar to how human experts make tax decisions, TKE executes a collection of algorithms over the graphs to address three problems for any given tax situation:

• What’s missing (complete data)
• What’s wrong (contradictions)
• Why (explaining recommendations)

By intelligently determining what questions to ask the tax filer, TKE minimizes the number of questions needed to get the information needed and make the appropriate recommendations. This functionality also lets TurboTax explain back the computational results in a fully personalized manner.

For example, through this technology, we can help our customers understand why they qualify for the earned income tax credit or why they are punished for a late payment… and all sorts of other factors or decisions that make taxes confusing to most of us. By building the engine to power this process and the various factors, we hope to increase each person’s confidence in the tax filing process and help them understand why certain factors may have changed for them from year to year.

As data scientists, we have the opportunity to significantly help millions of customers make better financial decisions every year, and we are looking for talented data technologists who are willing to build the next solution that can help their friends, family and community. If your expertise fits this area and you are interested in making a real difference in the financial lives of others, I encourage you to check out our career site to learn more.

1. Quarterly report on household debt and credit, Federal Reserve Bank of New York.

2. Office of Advocacy, (2017). Frequently asked questions about small business, U.S. Small Business Administration