Traditional methods of data analysis have long been used to detect fraud. They require complex and time-consuming investigations that deal with different domains of knowledge like financial, economics, business practices and law. Fraud often consists of many instances or incidents involving repeated transgressions using the same method. Fraud instances can be similar in content and appearance but usually are not identical.
The first industries to use data analysis techniques to prevent fraud were the telephony companies, the insurance companies and the banks (Decker 1998). One early example of successful implementation of data analysis techniques in the banking industry is the FICO Falcon fraud assessment system, which is based on a neural network shell.
Retail industries also suffer from fraud at POS. Some supermarkets have started to make use of digitized closed-circuit television (CCTV) together with POS data of most susceptible transactions to fraud.
Internet transactions have recently raised big concerns, with some research showing that internet transaction fraud is 12 times higher than in-store fraud.
Fraud that involves cell phones, insurance claims, tax return claims, credit card transactions etc. represent significant problems for businesses and government, but yet detecting and preventing fraud is not a simple task. Fraud is an adaptive crime, so it needs special methods of intelligent data analysis to detect and prevent it. These methods exists in the areas of Knowledge Discovery in Databases (KDD), Data Mining, Machine Learning and Statistics. They offer applicable and successful solutions in different areas of fraud crimes.
Two Main Techniques inf Fraud Detection: <br></br>Statistical and Artificial Intelligence.
1. Statistical data analysis techniques are:
- Data pre-processing techniques for detection, validation, error correction, and filling up of missing or incorrect data.
- Calculation of various statistical parameters such as averages, quantiles, performance metrics, probability distributions, and so on. For example, the averages may include average length of call, average number of calls per month and average delays in bill payment.
- Models and probability distributions of various business activities either in terms of various parameters or probability distributions.
- Computing user profiles.
- Time-series analysis of time-dependent data.
- Clustering and classification to find patterns and associations among groups of data.
- Matching algorithms to detect anomalies in the behavior of transactions or users as compared to previously known models and profiles. Techniques are also needed to eliminate false alarms, estimate risks, and predict future of current transactions or users.
Some forensic accountants specialize in forensic analytics which is the procurement and analysis of electronic data to reconstruct, detect, or otherwise support a claim of financial fraud. The main steps in forensic analytics are (a) data collection, (b) data preparation, (c) data analysis, and (d) reporting. For example, forensic analytics may be used to review an employee’s purchasing card activity to assess whether any of the purchases were diverted or divertible for personal use. Forensic analytics might be used to review the invoicing activity for a vendor to identify fictitious vendors, and these techniques might also be used by a franchisor to detect fraudulent or erroneous sales reports by the franchisee in a franchising environment.
2. For today’s Multi-Terabyte Hard Disk Drives and Big Data, Artificial Intelligence (AI) is best . The main AI techniques used for fraud management include:
- Data mining to classify, cluster, and segment the data and automatically find associations and rules in the data that may signify interesting patterns, including those related to fraud.
- Expert systems to encode expertise for detecting fraud in the form of rules.
- Pattern recognition to detect approximate classes, clusters, or patterns of suspicious behavior either automatically (unsupervised) or to match given inputs.
- Machine learning techniques to automatically identify characteristics of fraud.
- Neural networks that can learn suspicious patterns from samples and used later to detect them.
Other techniques such as link analysis, Bayesian networks, decision theory, land sequence matching are also used for fraud detection.
Machine learning and data mining
Early data analysis techniques were oriented toward extracting quantitative and statistical data characteristics. These techniques facilitate useful data interpretations and can help to get better insights into the processes behind the data. Although the traditional data analysis techniques can indirectly lead us to knowledge, it is still created by human analysts.
To go beyond, a data analysis system has to be equipped with a substantial amount of background knowledge, and be able to perform reasoning tasks involving that knowledge and the data provided. In effort to meet this goal, researchers have turned to ideas from the machine learning field. This is a natural source of ideas, since the machine learning task can be described as turning background knowledge and examples (input) into knowledge (output).
If data mining results in discovering meaningful patterns, data turns into information. Information or patterns that are novel, valid and potentially useful are not merely information, but knowledge. One speaks of discovering knowledge, before hidden in the huge amount of data, but now revealed.
Supervised and unsupervised learning
The machine learning and artificial intelligence solutions may be classified into two categories: ‘supervised’ and ‘unsupervised’ learning. These methods seek for accounts, customers, suppliers, etc. that behave ‘unusually’ in order to output suspicion scores, rules or visual anomalies, depending on the method.
Whether supervised or unsupervised methods are used, note that the output gives us only an indication of fraud likelihood. No stand alone statistical analysis can assure that a particular object is a fraudulent one. It can only indicate that this object is more likely to be fraudulent than other objects.
In supervised learning, a random sub-sample of all records is taken and manually classified as either ‘fraudulent’ or ‘non-fraudulent’. Relatively rare events such as fraud may need to be over sampled to get a big enough sample size. These manually classified records are then used to train a supervised machine learning algorithm. After building a model using this training data, the algorithm should be able to classify new records as either fraudulent or non-fraudulent.
Supervised neural networks, fuzzy neural nets, and combinations of neural nets and rules, have been extensively explored and used for detecting fraud in mobile phone networks and financial statement fraud.
Bayesian learning neural network is implemented for credit card fraud detection, telecommunications fraud, auto claim fraud detection, and medical insurance fraud.
Hybrid knowledge/statistical-based systems, where expert knowledge is integrated with statistical power, use a series of data mining techniques for the purpose of detecting cellular clone fraud. Specifically, a rule-learning program to uncover indicators of fraudulent behaviour from a large database of customer transactions is implemented.
Cahill et al. (2000) design a fraud signature, based on data of fraudulent calls, to detect telecommunications fraud. For scoring a call for fraud its probability under the account signature is compared to its probability under a fraud signature. The fraud signature is updated sequentially, enabling event-driven fraud detection.
This type of detection is only able to detect frauds similar to those which have occurred previously and been classified by a human. To detect a novel type of fraud may require the use of an unsupervised machine learning algorithm.
In contrast, unsupervised methods don’t make use of labelled records.
Some important studies with unsupervised learning with respect to fraud detection should be mentioned. For example, Bolton and Hand use Peer Group Analysis and Break Point Analysis applied on spending behaviour in credit card accounts. Peer Group Analysis detects individual objects that begin to behave in a way different from objects to which they had previously been similar. Another tool Bolton and Hand develop for behavioural fraud detection is Break Point Analysis. Unlike Peer Group Analysis, Break Point Analysis operates on the account level. A break point is an observation where anomalous behaviour for a particular account is detected. Both the tools are applied on spending behaviour in credit card accounts.
Also Murad and Pinkas focus on behavioural changes for the purpose of fraud detection and present three-level-profiling. Three-level-profiling method operates at the account level and points to any significant deviation from an account’s normal behaviour as a potential fraud. In order to do this, ‘normal’ profiles are created based on data without fraudulent records (semi supervised). In the same field, also Burge and Shawe-Taylor use behaviour profiling for the purpose of fraud detection. However, using a recurrent neural network for prototyping calling behaviour, unsupervised learning is applied.
Cox et al. combines human pattern recognition skills with automated data algorithms. In their work, information is presented visually by domain-specific interfaces, combining human pattern recognition skills with automated data algorithms (Jans et al.).