10 April The Irreplaceable Human Mind April 10, 2017By Jon Coss - Blog Manager fraud detection systems, General Algorithms, Fraud Detection, Prediction Models 0 At Pondera, we are often asked whether fraud detection algorithms will ever completely replace human investigators. And while I can’t address the “ever” part of the question, I can confidently state that it will not happen in the foreseeable future. One of the major reasons for this? Prediction models, like many people, struggle to distinguish between cause and effect.A Stanford University professor recently shared her studies on this topic which support many of our own findings. She noted that while prediction algorithms are excellent at finding patterns in large data sets, their effectiveness is limited because they struggle with determining causation. An example she used is that algorithms have been shown to help identify patients who should not receive hip surgery because they would likely die of other causes. However, the algorithms are unable to prioritize those patients who should receive the surgery.In several cases, the professor notes that correlation can be as low as 50%. And she properly notes that while this may be fine in certain situations, governments simply cannot conduct such high-risk experiments with social welfare, economic policies, and other important matters. And unlike controlled environments, such as those that use placebos to test medications, the real world is simply too messy and unpredictable to control all factors.This problem of causation identifies an important intersection between human reasoning and prediction algorithms. We believe that in complex, rapidly changing environments like fraud detection, effective detection systems combine the power of modern detection algorithms with experienced human reasoning.By leveraging the individual strengths of both machine and human learning, we can analyze massive data sets and make sense of the findings. We regularly use the system to find the problem and ask the human experts to help explain the problem. This makes the results actionable, which ultimately is what our government partners require. Related Posts A Reminder of Government’s Important Role in Helping Americans Regular readers of this blog know that we often focus our comments on the fraud and abuses in government subsidy programs. Our intent is almost always to point out solutions that can make these programs more effective, rather than to question the existence of the programs altogether. In fact, most Pondera employees worked for government agencies in the past and recognize the good that many programs deliver.The recent fires in California provide an example of government programs helping Americans in need. The fires, which tore through California’s wine country, including Napa and Sonoma, claimed over 40 lives and 7,000 structures, and displaced nearly 100,000 people. Entire neighborhoods were destroyed leaving families scrambling for shelter and food.A number of government agencies sprang into action to help those affected by the disaster. While most Americans are somewhat familiar with, for example, how FEMA responds to disasters, other efforts are less obvious but very important.For example, I took note of the combined efforts of the United States Department of Agriculture (USDA) and the California Department of Social Services (CDSS) to provide emergency food assistance to local residents. Using the Disaster Supplemental Nutrition Assistance Program (D-SNAP), CDSS offered a month of food benefits to those who qualify. This is in addition to other waivers such as allowing existing SNAP beneficiaries to purchase hot foods (many lost their homes and by extension their ability to prepare foods).Events like the fires in California, while heartbreaking, also provide us with a reminder of the important work done by federal and state government agencies. This is also a time to remember the important work that agencies do throughout the year to support Americans who truly need our assistance. We believe our job at Pondera is to help governments deliver better services by driving fraud, waste, and abuse out of their programs. The Dark Web, Illicit Sales, and Law Enforcement Efforts to Combat Illegal Markets While I don’t often review books on this blog, I feel compelled to share my thoughts on American Kingpin by Nick Bilton, which chronicles the history of the Silk Road. For those who don’t know, the Silk Road was a market on the dark web that sold drugs, weapons, poisons, and even human body parts. By the time it was shut down in 2013, the site was selling over $1 billion per year.The book offers fascinating insights into the dark web, the libertarian creator of the site, the investigators who worked to shut it down, and the political schisms that often make it possible to run sites like the Silk Road. And of course, the book has great relevance to the fraud detection business because fraudsters often acquire identities on the dark web to create fictitious businesses, file for tax refunds, and make fake unemployment insurance claims.While American Kingpin ended with the shutdown of the Silk Road and the prosecutions of the major actors behind the market, it is important to note that similar sites continue to operate on the dark web. In fact, just days after I finished reading the book, Attorney General Jeff Sessions announced that the FBI had shut down a similar site 10 times the size of the Silk Road. At the time this site was shut down last month, it contained 369,000 listings for drugs, weapons, malware, chemicals, counterfeit items, and more.This is a sobering reminder of the challenges facing law enforcement when dealing with anonymous browsers like TOR, the Bitcoin cryptocurrency, and international crime rings. The dark web is not going away. Neither is the demand for illicit items. It will be interesting to see how this “cat and mouse” games plays out over the coming years. Buried Pentagon Report Leads to Questions for Other Government Agencies Earlier this year, four government agencies – Commerce, Health and Human Services, Energy, and the Environmental Protection Agency—received letters from congress directing them to provide documents and comments detailing their efforts to “identify waste and… to achieve budget savings in the next five years.” The letter referenced a report from the Pentagon that identified a “clear path” to saving over $125 billion over five years, which was subsequently suppressed because of the dramatic findings.The Washington Post, which was mentioned in the letter from Congress, exposed the Pentagon’s internal study in December 2016. The Post explained the reason the Pentagon buried the study was that they feared Congress would cut their budget if they knew of the waste. Incredibly, the “clear path” to savings did not even require layoffs. Rather it would use attrition, early retirements, reductions in expensive contractors, and modern technology to streamline operations.To put the size of the problem in perspective, the study showed that the defense department paid over 1 million back-office staff to support 1.3 million active duty troops (the smallest number of troops since 1940). Thanks to these large numbers, the savings from streamlining could have led to reallocating up to $125 billion for troops and weapons and rebuilding the nation’s aging nuclear arsenal. But apparently, some Pentagon officials decided that protecting against budget cuts was more important.The four agencies who received the letter from Congress have until March 10th to respond. Their response must provide a copy of their internal reports similar to the Pentagon report, lessons learned for their department if they do not have a similar report, and any efforts the department has made to combat waste. Given that these four agency budgets total over $1 trillion, twice that of the Department of Defense, there should be ample opportunities for savings. Pondera’s Modified Bucket Theory I once worked for a manager that operated under what he called his “Bucket Theory”. His theory went like this: hire successful people, throw them in a “bucket”, and see who can climb their way out. Those that did, he explained, were the type that could succeed at this particular tech company. Those that couldn’t climb out were soon shown the exit. Pretty Spartan of him.When I founded Pondera, I thought it might be interesting to make modified use of the “Bucket Theory”. Here’s how my theory goes: hire skilled and dedicated people with diverse backgrounds and experiences, broadly define the problem that needs to be solved, then throw them in a “bucket” and ask them to come up with a solution for the problem. The only guidelines: treat each other with respect, expect mistakes, share in success, and “think outside the bucket”.Turns out that this modified bucket theory works pretty well. I’m constantly amazed by the innovations made by Pondera’s employees. And walking around the office, it’s not unusual to see a former FBI agent working with a PHD in Learning and Mind Sciences, an Unemployment Insurance investigator collaborating with the former founder of a Silicon Valley drone company, or a data scientist talking with a Certified Fraud Examiner.Since founding Pondera, I’ve read a number of articles about the importance of hiring staff from “adjacent” markets. For example, one article detailed how some skateboarders were able to help improve construction site safety equipment. And I think we’ve all seen images of football players in training sessions with ballet instructors. I imagine that the conversations between these two groups were equally as entertaining as the ones among Pondera’s employees.So why don’t more companies take this approach? I think there are two main reasons for this. First, many companies start with or develop the belief (sometimes arrogance) that their way is the only way. Like the proverbial hammer, they subsequently see every problem like a nail. The second reason: it can be very difficult to maintain a healthy company culture across such varied career experiences. Success depends on a clear and transparent vision combined with world class human beings. I personally feel very fortunate to work side-by-side with such people in the Pondera Bucket. The WannaCry Attack By this time, just about everyone has watched or read a news report about the WannaCry ransomware attack that hit the world’s computer networks on May 12th. Multiple variants of the program will likely attack computers for the foreseeable future, forcing individuals to pay bitcoin ransom or lose their data and causing serious harm to businesses including hospitals and governments.Plenty has been written about the source of the attack and how it works. So, while every “connected” person should read about WannaCry to help protect themselves against future attacks, I don’t see any need to cover this ground here. For me, though, two interesting facets of the story really stand out.First, I find it fascinating and somewhat inspiring that the attack was stopped by a 22-year-old vacationing cyber analyst who goes by the name MalwareTech; with assistance from his colleague Kafeine. These two, and countless others, operate in a world that most of us know almost nothing about to keep our systems safe. It reminds me of the classic Jack Nicholson speech from “A Few Good Men” where he excoriates Tom Cruise for challenging him while he protects our safety. Of course, in this example, there is no evidence of MalwareTech or Kafeine “fragging” any of their tech colleagues.The second interesting point I took form this attack was that most of us could have protected ourselves simply by updating our operating systems and virus protection software. This is a conversation I’ve had innumerable times with my own family. Of course, this also puts software manufacturers in the difficult position of patching years-old operating systems to accommodate those who won’t or can’t upgrade.Bottom line for me: this is just another reminder to remain vigilant and to be thankful for the computer techs who have dedicated their careers to protecting us from those who have chosen to attack us. I hope you can “handle that truth”. The Problem With Knowing What You Know I bet you cna’t bvleiee taht you can uesdtannrd waht you are rdnaieg. Unisg the icndeblire pweor of the hmuan mnid, aocdcrnig to rseecrah at Cmabrigde Uinervtisy, it dseno't mttaer in waht oderr the lterets in a wrod are, the olny irpoamtnt tihng is taht the frsit and lsat ltteer be in the rhgit pclae. The rset can be a taotl mses and you can sitll raed it whoutit a pboerlm. Tihs is bucseae the huamn mnid deos not raed ervey ltteer by istlef, but the wrod as a wlohe.The preceding paragraph, which has made its way around the Internet for years, can be really fun to share with friends. However, it also serves as a caution to anyone involved in fraud detection. In many ways, bad actors, knowingly or unknowingly, have depended on how the human mind works to perpetrate fraud schemes. Like the old expression goes, sometimes the best place for fraud to hide is in plain sight.This is especially true in government programs that process massive amounts of transactions and must adhere to a staggering number of program regulations. Traditional “top down” systems can analyze large data sets and find nothing wrong (after all, the first and last letters are in the right place). “Bottom Up” systems, on the other hand, will identify individual problems (the word is scrambled) but may miss the patterns in the data (this entire paragraph is scrambled). A common example of this is the medical provider that always “flies just below the radar” by maximizing claim amounts and frequencies.The best detection processes take both a “top down” and “bottom up” approach. They can identify individual transaction problems as well as identify patterns of bad behavior over time. In this way, you can make the old “80-20” rule work in your favor. 80% of improper payments are likely caused by 20% of program participants. If you only address each individual transaction, you’ll never run out of work but you also never really improve your program integrity efforts.Click here for an infographic on the "80-20 rule". Comment (0) Comments are closed.