Financial statements are incorrect for several reasons:
- anomalies occur (i.e. error, omission, fraud) and cascade through the statements
- some managers and executives may have strong incentives (i.e. bonuses) to deliberately inject error into financial statements
- estimates and judgment calls — even when made in good faith they may be widely off the mark
Our “Financial Health Check-Up” finds anomalies. Our investigation goes deep, we look at 100% of the general ledger entries.
Your shareholders, investors, board, and employees rely on your numbers to make wise decisions — efficient allocation of capital. Errors create uncertainty and damage your company’s reputation. Our financial risk analytics produced by artificial intelligence identifies anomalies.
We use the Ai Auditor for our investigation
MindBridge Ai Auditor is a revolutionary approach to detect anomalies – unintentional and intentional – by automating manual processes and providing a risk-based assessment to help organizations ensure compliance and minimize their exposure to financial loss and liability.
The Ai Auditor bridges the gap between human and artificial intelligence (AI) and enhances professional judgment. Advancements in AI enables a new class of analytics to analyze financial transaction flows to detect mistakes, errors and fraud.
The Ai Auditor generates actionable insights through an interactive, user-friendly visual interface to help organizations minimize risk exposure to the financial loss. It supports audit professionals to meet and exceed regulatory and industry standards. Industry leading professionals have proven that the Ai Auditor detects unusual human activities and transactions that incumbent systems cannot. In fact, the Bank of England selected the Ai Auditor in a worldwide competition.
The Ai Auditor uses artificial intelligence, machine learning, and traditional rule-based analytics. It was originally developed for forensic auditors. It is fully compliant with SAS 99, CAS 240, and ISA 240 and more! It is shaping the next generation of audit standards by working closely with academia and professional organizations.
We are making this high-value service available to organizations of all sizes. Depending on your needs, we provide reports: daily, monthly, quarterly, or annually.
Why do a financial risk assessment?
Anomalies occur in GLs. Our service finds them. Moreover, shareholders and regulators rely on correct financial information to make critical decisions. You do too! Understanding, early detection and correction of anomalies are critical to having the right data for managing operations, decision-making and protecting your reputation.
It is sad to say that the rate of fraud is increasing. The length of time to detect fraud is also increasing. Rules-based systems and data sampling are losing this battle. Clever people will figure out a way around rules. In fact, the higher the education level of the perpetrators, the higher the loss the organization suffers. To compound this problem, Lexis Nexis estimates that the cost to correct $1.00 of fraud is $2.40.
We have a better approach.
How does the financial risk assessment service work?
Our service gives you information to find problems.
- We begin with a review of the GL entries in your financial system.
- We find the anomalies and provide a report that pinpoints them.
- You investigate and correct potential issues before the anomalies cascade through your financial statements and reports.
Our reports give outcome measures of your financial information quality, reliability and accuracy. They provide a factual basis for quality improvement initiatives related to your reporting and internal controls. The report will show if your changes have strengthened your system.
|How Fraud is Detected||Percent of Cases|
|Law Enforcement Notification||2.5%|
|Surveillance / Monitoring||1.9%|
What is unique about our approach?
Our service is confidential and independent. We leverage advanced technology, including artificial intelligence, new advancements in machine learning, and data science for near real-time data analytics, pattern recognition and anomaly detection. We use over 27 control point indicators testing techniques on every GL entry.
Many organizations conduct internal reviews and assessment of financial transactions monthly, quarterly or semi-annually. The volume of financial transactions can be vast and need a team of full-time staff to work on the data. Some organizations use spreadsheets with manual and visual inspection to check, validate, and reconcile the information. These tasks are labour-oriented. time-consuming, tedious and expensive. Internal audit processes only find about 14% of fraud cases.
On the other hand, audit testing approaches use sampling methods and materiality thresholds. A regular audit usually sample tests less than 3% of the GL information. This approach detects about 4% of the fraud that is eventually found.
What about the fraud that isn’t found?
In contrast to the costly and time-consuming approaches used for validation of financial transactions, our service looks at 100% of the GL entries. We do it quickly and pinpoint anomalies. You investigate if the anomaly is accurately reflected, what occurred and take corrective action as needed. It saves time and money whether it is investigating past activities, detecting unacceptable behaviour or preventing possible transgression.
|Algorithms||MindBridge||Increasing Value of MindBridge Analysis|
|Business Rules||Packaged library of rules that adhere to industry standards |
All tests automatically performed
|Meets industry standards to detect known financial misstatements & errors|
|Statistical Models||Built-in recommended statistical tests |
All tests automatically performed
|Analysis includes industry recommended statistical model tests|
|Machine Learning||Built-in proven machine learning tests based on adaptation of proven methodologies|
All tests automatically performed
|Enhanced analysis with automated machine learning tests to uncover unknown financial misstatements & errors|
Four applications of our financial risk assessment
Schedule a demo
Posts — Financial Risk Assessment
Kingston Smith UK Chartered Accountancy adds MindBridge AI Auditor technology to its data analytics suite
MindBridge™ Analytics Inc. named one of Canada’s Companies-to-Watch in the 2017 Deloitte Technology Fast 50™ Awards
Thomson Reuters Tax & Accounting Reaches Agreement with MindBridge Analytics Inc. to Deliver Data Analytics Capabilities as Part of Audit Suite
FAQ — Financial Risk Assessment
The blockchain is a public ledger where transactions are recorded and confirmed anonymously. It’s a record of events that are shared among many parties. The blockchain is actually managed by distributed nodes. These nodes all have a copy of the entire blockchain. Nodes will forever come and go, synchronizing their own copies of the chain with those of other users. By distributing copies and access, the chain can’t simply “go down,” or disappear. It’s a decentralized system that is both sturdy and secure. More importantly, once information is entered, it cannot be altered. Here is blockchain explained in fewer than 100 words
You (a "node") have a file of transactions on your computer (a "ledger"). Two government accountants (let's call them "miners") have the same file on theirs (so it’s "distributed"). As you make a transaction, your computer sends an e-mail to each accountant to inform them.
Each accountant rushes to be the first to check whether you can afford it (and be paid their salary "Bitcoins"). The first to check and validate hits “REPLY ALL”, attaching their logic for verifying the transaction ("Proof of Work"). If the other accountant agrees, everyone updates their file.
This concept is enabled by "Blockchain" technology.
Surely it's more complicated?
Yes - but as a concept, not much more. Complexities come in the implementation and the journey to realize value from such implementations. The above example will, of course, be overly simplistic for some — but may be a starting point for others.
In a traditional environment, trusted third parties act as intermediaries for financial transactions. If you have ever sent money overseas, it will pass through an intermediary (usually a bank).
It will usually not be instantaneous (taking up to 3 days) and the intermediary will take a commission for doing this either in the form of exchange rate conversion or other charges.
The original blockchain is open-source technology which offers an alternative to the traditional intermediary for transfers of the crypto-currency Bitcoin. The intermediary is replaced by the collective verification of the ecosystem offering a huge degree of traceability, security, and speed.
In the example above (a "public blockchain"), there are multiple versions of you as “nodes” on a network acting as executors of transactions and miners simultaneously. Transactions are collected into blocks before being added to the blockchain. Miners receive a Bitcoin reward based upon the computational time it takes to work out:
- whether the transaction is valid and
- what is the correct mathematical key to link to the block of transactions into the correct place in the open ledger.
As more transactions are executed, more Bitcoins flow into the virtual money supply. The "reward" miners get will reduce every 4 years until Bitcoin production will eventually cease (although estimates say this won't be until 2140!). Of course, although the original blockchain was intended to manage Bitcoin, other virtual currencies, such as Ether, can be used.
How Blockchain Works
Why do I need to know about Blockchain?
There are three reasons why you need to know about Blockchain:
- Blockchain technology doesn\'t have to exist publicly. It can also exist privately - where nodes are simply points in a private network and the blockchain acts similarly to a distributed ledger. Financial institutions specifically are under tremendous pressure to demonstrate regulatory compliance and many are now moving ahead with Blockchain implementations. Secure solutions like Blockchain can be a crucial building block to reduce compliance costs.
- Block-chain technology is broader than finance. It can be applied to any multi-step transaction where traceability and visibility are required. The supply chain is a notable use case where blockchain can be leveraged to manage and sign contracts and audit product provenance. It could also be leveraged for votation platforms, titles and deed management - amongst myriad other uses. As the digital and physical worlds converge, the practical applications of Blockchain will only grow.
- The exponential and disruptive growth of blockchain will come from the convergence of public and private blockchains to an ecosystem where firms, customers and suppliers can collaborate in a secure, auditable, and virtual way.
Source: Blockchain explained... in under 100 words — Richard Bradley, Director, Deloitte
The number of accounting scandals is amazing. Most result in re-stating the accounts and some in major scandals. The issue of regulatory oversight is frequently in the press. However, even with enforcement increasing and getting penalties higher, a new accounting issue is never far behind. It continues to get worse. Just look at the impact on British Telecom’s stock because of the irregularities found in accounting in their Italian division (read about it here).
At MindBridge Ai focuses on solving one of the massive issues underlying these scandals. We are building an expert system to help both internal and external auditors. This provides us with higher levels of assurance about the financial statements they are sworn to certify.
And the baseline issue we are dealing with is the amount of financial data they need to consume. There has always been too much of it.
With Big Data, auditors are asked to “go fishing in a murky lake” and find accounting anomalies and irregularities for further review. Accountants and regulators agree to use statistical account sampling. Yet, the quality of the sample can only be measured after it has been sampled and analyzed. With the time pressure on providing audited results, if an irregularity or anomaly is found, the process has to start again. Moreover, this leads to costly re-statements which impact shareholder value and confidence in the audit firms.
To solve this, Mindbridge Ai leverages machine learning AI to provide auditors with a more highly justifiable sample before the audit begins. Our Ai Auditor service ingests and analyzes the entire leger. We pinpoint areas they should be investigating early on with a higher degree of justification against the standard, and currently accepted sampling techniques. This gives auditors a higher assurance rate. It helps them improve upon the current approaches that only meet the standard, and not move past it. This moves towards the answers we, the press and firms like British Telecom need.
MindBridge is bridging the gap between human and artificial intelligence by enhancing professional judgment across multiple industries. Recent advancements in artificial intelligence have enabled a new class of converged analytics to analyze financial transaction flows and better detect anomalies - unintentional mistakes/errors and intentional. Using algorithms based upon smart data science, MindBridge generates actionable insights through an interactive, user-friendly visual interface to help organizations minimize risk exposure to a financial loss while supporting audit professionals to meet and exceed regulatory and industry standards. Using the MindBridge Ai-Auditor is enhancing professional judgment as far less time is spent searching for anomalies and more time determining the underlying causes of the anomalies.
The MindBridge application has been tested by industry leading professionals and is proven to detect anomalous human activities and transactions that current incumbent systems cannot.
Year Founded: 2015
MindBridge Ai Auditor is a revolutionary approach to analyze financial transactions to detect anomalies - unintentional and intentional - by automating manual processes and providing a risk-based assessment to help organizations ensure compliance and minimize their exposure to financial loss and liability.
MindBridge AI Auditor - Enhancing Profesional Judgement
The MindBridge AI Auditor is bridging the gap between human and artificial intelligence (AI) by enhancing professional judgment across multiple industries. Recent advancements in artificial intelligence have enabled a new class of converged analytics to analyze financial transaction flows and better detect anomalies - unintentional mistakes/errors and intentional.
Using algorithms based on data science, MindBridge generates actionable insights through an interactive, user-friendly visual interface to help organizations minimize risk exposure to the financial loss while supporting audit professionals to meet and exceed regulatory and industry standards. The MindBridge application has been tested by industry leading professionals and is proven to detect unusual human activities and transactions that incumbent systems cannot.
Financial Transactions Analysis, Evolved
The tools currently used to analyze financial transactions are not keeping pace with the needs of today’s auditor and investigator professionals. Existing computer assisted audit tools are often time-consuming to use and do not provide the insights and analytics required to help effectively advise auditors or develop a comprehensive financial analysis. MindBridge offers intelligent audit technology to help increase the speed and accuracy of every audit and investigation.
Comprehensive analysis for accurate audits
Current audit and investigative techniques are limited by time and tools, restricting the financial analysis to random sampling and data filtering. What if you could review every financial transaction in the general ledger from every entry across every department?
With MindBridge there is no data set too large, meaning the system is capable of reviewing 100% of the data provided and calculating a risk score for every process or person that interacts with corporate data. This is how you can find more instances of financial misstatements suspicious financial discrepancies.
Intelligent anomaly detection to help you:
- Uncover more misstatements & potential fraud by reviewing 100% of corporate data
- Know where to look due to intelligent risk-scores
- Smarter control points that combine best practices and data science
- An intelligent system leveraging machine learning that adapts to your needs
Take financial audit efficiency to the next level
Automation is key to maximizing the efficiency of each financial audit or review your organization performs. By removing manual processes, it is possible to streamline time-consuming activities, which frees up team members to use their expertise more effectively.
MindBridge’s Ai Auditor helps you be more efficient by offering:
- Smart data ingestion of your financial records saves you time importing and shaping data files
- Automated risk-scoring is based on a blend of control points and anomaly detection algorithms to help guide you to entries that appear suspicious
- Automated insights recommend similar items to look at and which steps to take next
An unbiased analysis of each transaction history based on numerous control points and data science algorithms.
For maximum impact, the system is intuitive requiring little to no training meaning it can be used by anyone for the most basic of investigations, audits and all the way up to a forensic investigation.
A visual summary of all transaction data and risk scores so that each auditor and investigator can determine where to focus instead of using sampling techniques alone.
Better Meet Audit Standards
- Leveraging Artificial Intelligence to meet and exceed standards including:
- SAS 99 Fraud in a Financial Statement Audit
- IAS 240 / CAS 240 The Auditor’s Responsibilities Relating to Fraud in an Audit of Financial Statements
- Know where to look due to intelligent risk-scores
Automatically assigns a risk score to all transactions to focus audit, 100% coverage of all transactions.
Intacct Web Services, modern web-browser (Chrome or Firefox are preferable)
Price: contact: firstname.lastname@example.org
Machine learning is the subfield of computer science.
computers have the ability to learn without being explicitly programmed
It evolved from the study of pattern recognition and computational learning theory in artificial intelligence. Data scientists construct algorithms that learn from the data and adapt over time.
The focus is statistical learning. Machine Learning deals with predictions and not causality. It is effective at developing more complex relationships than humans can process. It performs well in nonlinear and interactions settings.
Examples of Machine Learning Application
- Assessing financial transactions - Advanced detection of anomalies through flow analysis of transitions. The MindBridge Ai Auditor uses machine learning to detect anomalies.
- Outage grid management – Predict storm damage and direct workflow and assets, thereby minimizing outages and operational costs
- Wire-Down Management – Identify key drivers in wire-down events and direct preventive measures
- Self-driving cars
- Classifying DNA sequences
Other applications for machine learning
- Adaptive websites
- Affective computing
- Brain-machine interfaces
- Classifying DNA sequences
- Computational anatomy
- Computer vision, including object recognition
- Detecting credit card fraud
- Detection of network intruders or malicious insiders working towards a data breach
- Email filtering
- Game playing
- Information retrieval
- Internet fraud detection
- Marketing machine learning control
- Machine perception
- Medical diagnosis
- Natural language processing and understanding
- Optimization and metaheuristic
- Online advertising
- Recommender systems
- Robot locomotion
- Search engines
- Sentiment analysis (or opinion mining)
- Sequence mining
- Software engineering
- Speech and handwriting recognition
- Financial market analysis
- Structural health monitoring
- Syntactic pattern recognition
- User behavior analytics
Machine learning compares the data set by looking at Row 1 and its columns vs Row 2 and its column data. Then, Row 3, etc. The MindBridge Ai-Auditor ingests 100% of the file. It then analyzes 100% of the file with 100% of the rest of the file. This is hard to explain as this is the background of how the MindBridge Ai-Auditor works, but it takes data from the GL and breaks them down into ‘nodes’ where the machine learning occurs.
We use this approach in all of our financial risk assessment services and examine every transaction.
Data Set — An Example
The example follows a simple use-case: CITY POPULATION. Imagine every dot represents 1 person in a city.
Those circled by Green show that it’s within normality. In that, the large part of the population lives near to one another. There isn’t anything odd about where they live. That’s not to say that once you dive in you won’t find anything (there might be cases of crime, theft, etc), but from a high-level, it looks normal.
Then, Orange is starting to show that the distribution of people is starting to scatter. This is odd. Why is that? Why are they living slightly further away from the general population?
Now, those in Red are real outliers. Why are they so far from not only the general population but also from one another? What is the story behind these dots?
This is what you would consider a High-Risk %, and would need further analysis.
Think of MindBridge Ai-Auditor like that when it breaks the file down. Think of machine learning as everything a human cannot do. There is absolutely no way a human would be able to ingest 100% of the file for 100,000 Journal Entries. More so, a person would not be able to properly map out every single entry into a format that makes sense.
At present, the MindBridge Ai-Auditor only 1 GL can be analyzed. It’s ideal to have 12 or more months of data rolled-up into 1 file.
Cohort Analysis (ie., analyzing multiple files, such as 12 files where 1 file is 1 month) is something that’s coming in the future in our sub-ledgers update.
Read Mansbridge's Story.
Data for machine learning
There is not a 'one size fits all' answer to answer the question: "What is the minimum sample size required to train a deep learning model. The amount of training data you require is dependent on many different aspects of your experiment:
- How different are the classes that you're trying to separate? e.g. if you were just trying to classify black versus white images then you'd need very few training examples! But if you're trying to solve ImageNet then you need training data on the order of 1000 examples per class.
- How aggressively can you augment the training data?
- Can you use pre-trained weights to initialise the lower layers of your net? (e.g. using weights trained from ImageNet)
- Do you plan to use batch normalization? It can help reduce the amount of data required.
Data scientist work to squeeze maximum advantage from a small training dataset to give the best results.
Traditional analytics rely on rule-based methods for anomaly detection. These decision rules follow simple Boolean logic: if a vendor address matches an employee address and its wire transfer account matches the employee bank account, then it is likely a fictitious vendor.
Machine learning is a useful type of AI that is able to learn without predefined decision rules. Machine learning constructs its own decision tree based on meta-tagged data, e.g., “red flag” or “not,” to decide how “red flag” transactions are related. Machine learning applies the learned logic to new data and is remarkably adept at making the right decision. Machine learning’s ability to learn from a complex array of data and not just a few variables leads to greater accuracy.
Another type of machine learning, called “unsupervised learning,” constructs decision trees without meta-tagged data; it identifies patterns of interest and anomalies using its own decision-making criteria. This allows fraud examiners to find new forms of fraud not previously detected or codified into rules-based methods. Both supervised and unsupervised machine learning systems are self-refining, in that they become more accurate as more data is encountered.
The MindBridge Ai-Auditor machine learning translates every incoming GL into a language the machine understands (the 5 account mapping feature). Because of this translation, the machine is able to understand the monetary flows within a GL and identify unusual transactions. Traditional CAAT tools don’t do that, they simply scan numbers in isolated (for example show me all weekend entries). They don’t need to understand the GL to find such transactions.
Machine learning translates the GLs use in our suite of financial compliance risk services.
Existing practices in financial anomaly detection typically use rules-based systems to find breaches of control. An example of such a rule is a transaction amount limit.
Using rules-based systems is the backbone of today’s auditing methods. However, often this approach fails to find material financial misstatements and fraud. Clever fraudsters understand these rules and get around them. Rules only capture what is explicitly coded into them.
Rules are designed and implemented for each known circumstance that requires control or management. This means rules based systems will not catch unanticipated scenarios. Even with the example of the transaction amount limit, the commonly known way to ‘work around’ simple limit rules is transaction splitting. Often the rules themselves create the opportunity or scenario for the exploit. The data from the Association of Certified Fraud Examiners shows that the higher the education level of the perpetrators, the higher the loss the organization suffers and in most scenarios the perpetrators have at least a University level education.
Tip-off most likely way to catch a fraudster today
The most likely means of which a fraudster gets caught today is through a tip-off, roughly 40%, and industry associations tell organizations to add “fraud hot lines” to gather these tips. Conversely, automated controls and IT systems based on rules only catch a small percentage of scenarios — approximately 3%.
The rate of fraud is increasing and the time to detect fraud is also increasing. In almost every measurable way rules based systems which use data sampling are losing this battle. To compound the problem, Lexis Nexis estimates that the cost to correct $1 of fraud is $2.40.
It’s time for a change because clever people will figure out a way around rules.
It is often the case that it is not a single transaction that indicates an anomaly but a group of transactions such as a recurring monthly event. As such, normal outlier detection does not work as it is often a set of transactions that individually may seem to be normal or acceptable practices but collectively do not follow normal or acceptable practices. To address this, outlier detection is built in several layers to consider how rare a given business process may be and the outlier score of transactions based on other transactions in its group, and the ledger.
Anomalies such as financial misstatements, or fraud, are often not detected because they are carefully hidden among other similar transactions. Sophisticated fraudsters hide their work among similar account interactions and values.
This is where outlier systems need to consider many dimensions of the data at once. While human beings are good at seeing an outlier in 2 or 3 dimensions, a machine can do the same work tirelessly, considering 10 or more dimensions at a time. This capability helps machines to spot the outliers which are hiding next to normal activity and within an established process.
Below is a comparison of MindBridge versus traditional audit analytics tools.
Traditional Audit Analytics Tools
Coverage of testing
|100% of known areas of interest||100% of known and unknown cases||MindBridge|
|Trusted, but outdated technology||Breakthrough technology, with growing evidence of its effectiveness|
(MindBridge positioned to surpass)
Knowledge curve (coding)
|100% of known areas of interest||Not required|
Ease of use (user interface)
|Cumbersome, requires repetitive, extensive user training||Highly visual, intuitive with little-to-no training|
|Time-consuming to set up rules for each client file||Not required|
|Dependent on ERS resource||Self-service||MindBridge|
Composition & depth of algorithms
|Rules are hand-crafted scripts and results are logged.||Packaged industry standard rules enhanced with automated, scientific algorithms, results are logged and exported||MindBridge|
|Rules are created to handle each case||Once flagged, machine learning automatically excludes them from future analysis|
|Built-in, automated “smart ingestion” leveraging machine learning|
|Subjective & selective: reliant on professional skepticism and experience to find potential financial misstatements||Objective & inclusive: AI risk-based analytic tests prescribed by the Center for Audit Quality, plus extended analysis that further improves audit assurance|
This is an excellent approach. Most organizations under 500 employees do not have an internal audit process. It will give you facts to show those who think you are too small that you are exposed to the same risks as big companies.
Today organizations face an unprecedented confluence of risks. Two-thirds of CEOs see more threats to their business than opportunities. To stay competitive, you must pursue two parallel strategies: risk resiliency and risk agility.
Forward-looking companies have both the solid infrastructure and processes to help them weather any storm, as well as the flexibility to move quickly to meet new opportunities.
A comprehensive internal audit function plays a critical role in helping your organization achieve good governance—by providing an independent and objective assessment of your risk management strategies and control frameworks.
You can learn about how we use advanced financial compliance analytics to conduct a financial risk assessment in audit, internal audit and financial due diligence for merger and acquisition work.
You may find the Top 14 Financial Frauds of All Time to be of interest.
Machine learning is the subfield of computer science.
computers have the ability to learn without being explicitly programmed
There are many machine learning applications.
Machine learning evolved from the study of pattern recognition and computational learning theory in artificial intelligence. Data scientists construct algorithms that learn from the data and adapt over time.
The focus is statistical learning. Machine learning deals with predictions and not causality. It is effective at developing more complex relationships than humans can process. Machine learning performs well in nonlinear and interactions settings.
Examples of machine learning application
- Assessing financial transactions – advanced detection of anomalies though flow analysis of transitions. The MindBridge Ai Auditor is an excellent example.
- Outage grid management – predict storm damage and direct workflow and assets, thereby minimizing outages and operational costs
- Wire-Down Management – identify key drivers in wire-down events and direct preventive measures
- Self-driving cars
- Classifying DNA sequences
- Other applications for machine learning include: adaptive websites, affective computing, bioinformatics, brain-machine interfaces, cheminformatics, classifying DNA sequences, computational anatomy, computer vision, including object recognition, detecting credit card fraud, detection of network intruders or malicious insiders working towards a data breach, email filtering, game playing, information retrieval, internet fraud detection, marketing machine learning control, machine perception, medical diagnosis, economics, natural language processing, natural language understanding, optimization and metaheuristic, online advertising, recommender systems, robot locomotion, search engines, sentiment analysis (or opinion mining), sequence mining, software engineering, speech and handwriting recognition, financial market analysis, structural health monitoring, syntactic pattern recognition, user behavior analytics, translation
Learn about how we use machine learning for financial risk assessments.