Artificial Ignorance is a term that relates to machine learning and anomaly analysis, but as a concept, it can remind us to put in a process that ignores the noise of data overload and to focus on solving a problem, winning an opportunity, or opptimizing a business. In this post, we tie this to an important risk management concept: Identify, Measure, Monitor, and Report.


Initially, Artificial Ignorance sounded like a parody that expressed a blissful retreat from the hype and fears of Artificial Intelligence. Synonyms for ignorance includes bewilderment and unlearned, portraying Artificial Ignorance is an automated way to do nothing.

It is not. In this case, ignorance is the act of ignoring unimportant data, allowing you to focus on what is important and necessary in order to create value.


Artificial Ignorance is a type of machine learning. It is mostly associated with monitoring log files and network traffic to spot security intrusions, identify root cause of system crashes, and other issues.

See the animated diagram below for this quick explanation:

  • In the normal course of business, your organization generates data activity.
  • A machine drops in and monitors the activity over time in order to learn what is normal.
  • If something new enters and affects your environment, the machine identifies what is not normal, or anomalies, at very fine detail.
  • It brings to your attention potential problems or perhaps, opportunities.

Since it is machine learning, issues are picked up that have not already been documented, mitigating risk against the unknown.


The expression, “Can’t see the forest for the trees” is used to describe someone who is overcome by detail and fails to see the big picture. In this post, we consider the opposite, where value is derived by seeing specific trees for the forest. Depending on the business challenge, you may be looking for opportunites (trees with nuts) or problems to be fixed (diseased trees).

Mobile computing, real time analytics, and financial transactions from the edges of your world generates huge amounts of data in an instant. Depending on the situation, it may be optimal to ignore most of it (the forest) and focus on key events (some of the trees), optimizing the decision process.

Outside of the network infrastructure scenarios described above, the concept of Artificial Ignorance can be applied closer to the decision making process if you can get creative with the right tools and data assets in order to identify what is not normal (or what is special).


A deviation in consumer behavior could flag a new business opportunity. Deviation of compliance based events could contribute key facts to a fraud examination and provide a compelling example to auditors of compliance monitoring and controls. Here are two examples:

  • A trader action that deviates from what is considered normal trade activity could trigger a red flag. It may be worth monitoring that trader by additional and more descriptive means (chat, voice, review trade history, etc.).
  • For trading strategy, the “something new” described in the animated diagram above, could be non traditional data like weather or location intelligence that puts a particular risk measure out of normal limits.


A standard process in Risk Management is to identify, measure, monitor and report. Measuring, monitoring, and reporting comes to naught if relevant issues can’t be identified. There is often the desire to bring in more and more data but the tools need to be put that identifies what is important.

There is a lot of excitement and hype that comes with big data, real time analytics, artificial intelligence, the fintech revolution, and so forth. However, there is still a fundamental need to focus on business strategy (conceptualize and act on what is important) and data strategy (capture and identify what is important).

Depending on your business drivers, you probably don’t need all of the data that is being created. This is a good concept to keep in mind. As it relates to Artificial Intelligence, there could be very good reason to apply Artificial Ignorance first.

“Use Location Intelligence to Combat Financial Crime”

This video accompanies the article by Kenneth Goodwin, Jeanensis Capital Markets, and Paul Lashmet, North Castle Integration called, , featured in TabbFORUM.

Intelligence – artificial or real – is only as good as the information it uses. Location intelligence helps contextualize a situation and can augment machine learning and other applications of artificial intelligence. How can location intelligence be applied to regulatory compliance initiatives to help combat financial crime?

Intelligence (artificial or real) is only as good as the information it uses. A higher volume of relevant information provides deeper context to a situation, resulting in heightened intelligence, increased value, and better outcomes.

Location intelligence is a data asset that helps contextualize a situation and can augment machine learning and other applications of artificial intelligence. This post considers how location intelligence can be applied to regulatory compliance initiatives, specifically fraud examination and forensic audit, to combat financial crime.

Fraud Examination and Forensic Audit

Fraud examination is the discipline of resolving allegations of fraud from tips, complaints, or accounting clues. It involves obtaining documentary evidence, interviewing witnesses and potential suspects, writing investigative reports, testifying to findings, and assisting in the general detection and prevention of fraud*.

Forensic audit is the process of investigation used to build a case that supports fraud examination. It is the intersection of financial principles and the law, and therefore, applies the following:

  1. Technical skills of accounting, auditing, finance, quantitative methods, and certain areas of the law and research;
  2. Investigative skills for the collection, analysis and evaluation of evidential matter; and
  3. Critical thinking to interpret and communicate the results of an investigation.

Points 2 and 3, above, are particularly relevant to this post. The collection and analysis of evidential matter needs a variety of data assets to support a comprehensive investigation. Critical thinking – sometimes referred to as lateral thinking, or thinking “outside the box” – is a disciplined approach to problem solving and guides our thought process and related actions. Critical thinking is required to contextualize patterns and connections across evidential matter.

Location Intelligence Is Context

Think about where you are right now. You may be at a specific address. If you have location services enabled on your phone, you are also located at specific coordinates relative to the rest of the world. However, the intelligence of your location is more than that.

The neighborhood that you are in can be characterized by demographics and consumer preferences. It also can be described in relation to the proximity of other neighborhoods that may have similar or very different characteristics. The people around you have mobile devices that are interacting with social media, streaming a live event, or making a purchase. Video is capturing movement, and machine sensors are analyzing usage and scheduling maintenance.

Location intelligence applies the multiple layers of information that surround you. The better you are able to logically connect these layers of information, the more location intelligence you have.

Back to Evidential Matter

Location intelligence continues to grow as a critical component of analytics, and it is being applied to more and more scenarios across industries through social media, connected devices, distributed systems, the internet of everything, and overlaying all of that with just about any dataset that can be collected.

In financial services, location intelligence provides an important and actionable level of information that ties together a customer profile, from on-boarding to know-your-customer and financial crime investigations. Referring back to Fraud Examination and Forensic Audit, above, location intelligence can be a critical component of evidential matter.

A Scenario

Party A is a bank customer that, by all accounts, is squeaky clean.

  • Party A executes a financial transaction with Party B from a place Party A has never been to before.
  • Party B registered their place of business as being in an upscale business park, but a satellite view shows that the actual location is in an abandoned industrial area.
  • Party B makes many transactions with Party C that very closely correlates to the sum that was originally sent from Party A.
  • Party C is located in very close proximity to a HIFCA designated zone. [To get a sense of what proximity risk is, look at High Intensity Drug Trafficking Areas (HIDTA) and High Intensity Financial Crime Area (HIFCA).


Location Intelligence - How it works [Graphic by Paul Lashmet]

Location Intelligence – How it works [Graphic by Paul Lashmet]

Should Party A be investigated? It is a questionable circumstance, at least.

As it relates to forensic audit, location intelligence provides additional layers of information that tighten the interrelationship among auditing, fraud examination and financial forensics in a dynamic way that adapts to political, social, and cultural pressures over time.


Fraud examination and forensic audit encompasses much more than just the review of financial data; it also involves techniques such as interviews, statement analyses, public records searches, and forensic document examination to identify questionable circumstances.

Location intelligence can help identify transaction anomalies more quickly, verify customer place of business visually and more efficiently, and flag sensitive cross-border conditions and proximity risk. All of these are vital in securing the proper documentation needed in a robust forensic examination.


The organization’s obligation is to report suspicious activity, not to stop it, by submitting a SAR (Suspicious Activity Report). There are two levels to this:

  • Level 1 – “The Sniff Test”: A questionable activity or a correlation of circumstances is identified (“Something seems fishy here”).
  • Level 2 – Investigation: A disproportionate amount of time can be spent manually collecting supporting documentation. A good set of data access tools that links relevant data points, including location intelligence, can optimize this process, making it faster and with better quality.

This is article was first published in TabbFORUM “Rebuilding Risk and Compliance for the Age of Oversight”, sponsored by Cognizant.
Authors: Kenneth A. Goodwin Jr. of Jeanensis Capital Markets and Paul Lashmet of North Castle Integration.