Tag Archives: investigation software

China building big data platform for pre-crime

Re-posted by Crime Tech Solutions – Your Source for Investigation Software
It’s “precrime” meets “thoughtcrime.” China is using its substantial surveillance apparatus as the basis for a “unified information environment” that will allow authorities to profile individual citizens based upon their online behaviors, financial transactions, where they go, and who they see. The authorities are watching for deviations from the norm that might indicate someone is involved in suspicious activity. And they’re doing it with a hand from technology pioneered in the US.
Tiananmen_Square_Beijing_China_1988_1-640x447As Defense One’s Patrick Tucker reports, the Chinese government is leveraging “predictive policing” capabilities that have been used by US law enforcement, and it has funded research into machine learning and other artificial intelligence technologies to identify human faces in surveillance video. The Chinese government has also used this technology to create a “Situation-Aware Public Security Evaluation (SAPE) platform” that predicts “security events” based on surveillance data, which includes anything from actual terrorist attacks to large gatherings of people.
The Chinese government has plenty of data to feed into such systems. China invested heavily in building its surveillance capabilities in major cities over the past five years, with spending on “domestic security and stability” surpassing China’s defense budget—and turning the country into the biggest market for security technology. And in December, China’s government gained a new tool in surveillance: anti-terrorism laws giving the government even more surveillance powers and requiring any technology companies doing business in China to provide assistance in that surveillance.
The law states that companies “shall provide technical interfaces, decryption and other technical support and assistance to public security and state security agencies when they are following the law to avert and investigate terrorist activities”—in other words, the sort of “golden key” that FBI Director James Comey has lobbied for in the US. For obvious reasons, the Chinese government is particularly interested in the outcome of the current legal confrontation between the FBI and Apple over the iPhone used by Syed Farook.
Bloomberg reports that China is harnessing all that data in an effort to perform behavioral prediction at an individual level—tasking the state-owned defense contractor China Electronics Technology Group to develop software that can sift through the online activities, financial transactions, work data, and other behavioral data of citizens to predict which will perform “terrorist” acts. The system could watch for unexpected transfers of money, calls overseas by individuals with no relatives outside the country, and other trigger events that might indicate they were plotting an illegal action. China’s definition of “terrorism” is more expansive than that of many countries.
At a news conference in December, China Electronics Technology Group Chief Engineer Wu Manqing told reporters, “We don’t call it a big data platform, but a united information environment… It’s very crucial to examine the cause after an act of terror, but what is more important is to predict the upcoming activities.”
__
(NOTE: Crime Tech Solutions is an Austin, TX based provider of crime and fraud analytics software for commercial and law enforcement groups. We proudly support the Association of Certified Fraud Examiners (ACFE), International Association of Chiefs of Police (IACP), Association of Law Enforcement Intelligence Units (LEIU) and International Association of Crime Analysts (IACA). Our offerings include sophisticated link analysis software, comprehensive crime analytics with mapping and predictive policing, and criminal intelligence database management systems.)

Is the Most Dangerous Company in America?

Posted by Tyler Wood, Operations Manager at Crime Tech Solutions
ciaThis is a very interesting read about the current big data analytics darling, Palantir Technologies. The article from GS Early appears on the Personal Liberty website HERE.
The original article follows…
I was reading my newsfeeds and I came across a very interesting story about this highly secretive company that is apparently buying up as much Palo Alto, California real estate as it can get its hands on.
But that isn’t even the most interesting thing about them. What piques my interest is how this start-up that just added another $450 million to its funding — it now has about $20 billion in funding — got its money.
The company is called Palantir Technologies. If the name sounds familiar, it’s because it comes from JRR Tolkein’s trilogy of fantasy novels. In The Fellowship of the Ring, Saruman the wizard uses the Palantir of Orthanc, an indestructible sphere of dark crystal, to see into the future and communicate across the world.
That sounds geeky and innocuous enough, no?
But Palantir the company’s biggest clients are the FBI, SEC and the CIA. It is a Big Data company that also has corporate clients, but much of the work — from what anyone can tell — comes from hush-hush projects for the U.S. intelligence community.
This crystal ball of a company sounds less like a quaint fantasy than a key element of the “thought police” in Philip K. Dick’s dark science fiction tale “The Minority Report.”
In “The Minority Report,” the police used computers to predict when and where a crime would occur and apprehend the perpetrator before he actually committed the crime.
The crazy thing is, we’re now living in a world where Big Data makes that possible.
First, let me explain what Big Data is. Basically, now that our lives are completely recorded in various media — traffic cameras, debit card transactions, loyalty cards, phone calls, television shows watched, internet, social media, SMS texts, etc. — computers are powerful enough now to sort through all this data from all these sources and come up with predictive patterns for individuals and groups.
This is a very hot area for retail stores. But it also has enormous implications in a variety of industries; and many of them are helpful.
It is certainly a tool that law enforcement and our intelligence services would find valuable to root out potential terrorists or groups that are planning some terrorist act. It is also useful to find people who are attempting to elude authorities. And being able to get ahead of the some of the more devious players on Wall Street and their illegal trading schemes would be nice.
But you can see where this could be turned on Americans, just as easily as the NSA turned its endeavors on to less than righteous paths.
Palantir is raising eyebrows in the epicenter of digital startups because most companies, once they reach a certain size, move out of Palo Alto and build a campus in some surrounding town.
Not Palantir. It now owns about 10-15 percent of all the available space in Palo Alto, more than 250,000 square feet. It is the fourth most valuable venture backed company in the world.
The irony in the article was, the concern wasn’t about its biggest client or what it’s doing for the CIA, it was the fact that it’s eating up all the available commercial space in Palo Alto and not leaving room for new startups.
My concern is a bit deeper. The CIA could have quietly gone to one of the major Big Data firms like Accenture or IBM and worked with them on whatever it is they needed. But instead they essentially built their own company, where there are much fewer people to throw up roadblocks to the work being done. I have no problem with government using Big Data to protect us; my concern is when intelligence and enforcement agencies have unfettered use of it.
But, there’s no turning back the clock. We are in the Big Data, cybersecurity age and plenty of these companies already exist. Usually their goal is help their clients sell more lavender soap in February or figure out what kind of salad greens a 37-year-old mother of two prefers to buy at 7 p.m. on a Wednesday evening.
On a fundamental level, it’s best to keep your digital footprint light. Make sure you have secure passwords that aren’t just 1234 or your pet’s name. Most browsers have an “incognito” mode that won’t track your browser history. But truth be told, if someone really wants your history, they can get it.
If you’re more serious about hiding your footprints, look into encrypted services like Tor (www.torproject.com) that will protect against traffic analysis (browser history, instant messaging, etc.). It’s free and very good.
Transactions in bitcoins is a way to keep your footprint light in the marketplace.
And if you’re looking to make money on the trend, there are any number of companies that are at the forefront of cybersecurity (Palo Alto Networks, FireEye, Synamtec) and Big Data (Accenture, IBM, Teradata, Oracle).
–GS Early
(NOTE: Crime Tech Solutions is an Austin, TX based provider of crime and fraud analytics software for commercial and law enforcement groups. We proudly support the Association of Certified Fraud Examiners (ACFE), International Association of Chiefs of Police (IACP), Association of Law Enforcement Intelligence Units (LEIU) and International Association of Crime Analysts (IACA). Our offerings include sophisticated link analysis software, comprehensive crime mapping and predictive policing, and criminal intelligence database management systems.)

Technology and the fight against terrorism

Posted by Crime Tech Solutions
From CNN…
Terrorist-picture-scan-750x500http://money.cnn.com/2015/11/24/technology/targeting-terror-intelligence-isis/index.html?iid=ob_lockedrail_bottomlarge&iid=obnetwork
(NOTE: Crime Tech Solutions is an Austin, TX based provider of crime and fraud analytics software for commercial and law enforcement groups. We proudly support the Association of Certified Fraud Examiners (ACFE), International Association of Chiefs of Police (IACP), Association of Law Enforcement Intelligence Units (LEIU) and International Association of Crime Analysts (IACA). Our offerings include sophisticated link analysis software, comprehensive crime mapping and predictive policing, and criminal intelligence database management systems.)

Best Practices – Geospatial Crime Mapping

Posted by Tyler Wood, Operations Manager at Crime Tech Solutions.

Crime mapping technology is a powerful and valuable tool for law enforcement. The ability to represent crime statistics visually – in a meaningful way – is helping police forces across America to analyze, understand, predict, and even prevent crime. It is, however, important to use caution when using such powerful tools, in order to prevent incorrect analyses of crime statistics that may hinder, rather than help, an investigation.
Specifically, there are a few key mistakes which should be avoided when utilizing this sort of predictive technology.

  1. Obviously, crime reporting should be thorough and detailed. Crime mapping technology takes a great many factors into consideration when developing a visual analysis of a certain area. The more detailed the input is, the more accurate the predictions and visualizations will be.
  2. Not every crime occurs at a specific street address. Certain crimes, like personal theft, may not be noticed until hours or even days after they occur, making it difficult to define an exact location at which the crime was committed. Analysts should take care to visualize each location in which it could have occurred.
  3. When developing a crime map of an area, analysts should take care to split the data between daytime and nighttime hours, as many areas have significantly different rates of crime depending on the time of day. If time is not taken into consideration, data can become skewed and law enforcement can develop a warped picture of the area.
  4. It is also important for analysts to consider other factors that affect crime reporting within a specific area. For example, petty crimes may be reported less often in lower-income neighborhoods. Care should be taken to consider the demographics and socioeconomic standings of the area being mapped in order to provide more context which can help analysts to more accurately predict and prevent crime.
  5. Sentinel Visualizer - Geospatial AnalysisCombining, where possible, the functionality of link analysis into the crime mapping process brings powerful additional functionality. This ability to link, not only statistical, but entity-specific data is a potential game changer.

The role of crime mapping in the world of law enforcement is gaining popularity. Unfortunately, for many police departments, the cost of a full suite of software from category leader, ESRI is prohibitive. Still, there are options available… notably, CrimeMap Pro from Crime Tech Solutions.

___

(NOTE: Crime Tech Solutions is an Austin, TX based provider of crime and fraud analytics software for commercial and law enforcement groups. We proudly support the Association of Certified Fraud Examiners (ACFE), International Association of Chiefs of Police (IACP), Association of Law Enforcement Intelligence Units (LEIU) and International Association of Crime Analysts (IACA). Our offerings include sophisticated link analysis software, comprehensive crime mapping and predictive policing, and criminal intelligence database management systems.)

Link Analysis and Crime – An examination.

Posted by Tyler Wood, Operations Manager at Crime Tech Solutions
Pic003The topic of fraud is widely discussed, and the focus of thousands upon thousands of articles. Television shows such as Crime, Inc and American Greed have become popular due, in part, to our fascination with the topic of fraud.
The organizations that are affected by fraud are also fascinated… but for entirely different reasons. Some estimates suggest that the US economy loses 11 trillion dollars each year due to one form of fraud or another. It’s little wonder, therefore, that the companies most frequently defrauded have been heavily investing in anti-fraud technologies at an increasing rate over the past decade or more.
The biggest problem with fraud, of course, is that it is always evolving in a very Darwinian fashion. Like a living, breathing entity, fraud schemes change over time in order to survive. As the targets of fraud schemes put new policies, procedures and/or systems to deter the activities, the schemes modify and find new ways to survive.
v1
So, since the nature of criminal activity is such that they constantly change, how do investigators find a fool proof methodology to ensure they are 100% safe from them? The answer, of course, is that they can’t. They never will; at least not until we live in a world such as the one depicted in the 2002 film Minority Report, starring Tom Cruise. In that movie, criminals are arrested prior to committing a crime based upon the predictions of psychics called ‘Precogs’. Corporations and individual targets of fraud can only wish.
Nope, there are no Precogs running around locking up would-be practitioners of fraud that would protect banks, insurance companies, Medicaid and Medicare programs, victims of Ponzi schemes, victims of identity theft, and countless others. Instead, organizations rely upon skilled knowledge workers using purpose-built crime and fraud analytics technology that can detect anomalies in patterns, suspicious transactions, hotspot mapping, networks of fraudsters, and other sophisticated data analytics tools.
v4
Crime and fraud analytics
Any discussion of analytics and investigation software must touch upon the topic of ‘big data’. No longer just a buzz word, big data literally fuels the insights gathered by organizations in every area of business. Naturally, then, organizations who have been traditionally targeted by fraudsters have increasingly invested in crime technology such as investigation software and analytics in order to exploit the phenomenon.
gotbigdata.pngOf course, big data in and by itself does nothing. It just sits there. Nobody has ever yelled “Help! We’ve been defrauded! Call the big data!” Big data is only useful when it can be transformed into ‘smart data’. In other words, understanding the big picture of costly fraudulent activities is not akin to understanding the specifics of ‘who’ is defrauding you, and ‘how’ they are doing it.
Those questions can best be answered through the powerful data mining and link analysis software tools offered by Austin, TX based Crime Tech Solutions in partnership with Sterling, VA based Visallo. Effective link analysis complements big data analytics platforms, helping to expose previously undetected fraud, and the entities (people or organizations) committing it.
Link Analysis – Transforming big data into smart data
By definition, link analysis is a data analysis technique that examines relationships among people, places, and things. As a visual tool, link analysis provides users a powerful method to quickly understand and ‘see’ what is happening. Because of this, it is widely used by financial institutions such as banks and insurance companies to uncover criminal networks, improve fraud investigations, detect insider fraud, and expose money laundering schemes. Similarly, government agencies use link analysis to investigate fraud, enhance screening processes, uncover terrorist networks and investigate criminal activities.
At Crime Tech Solutions, we liken the question of how to detect and deter fraud to ‘How do you eat an elephant?’ The answer, of course, is one bite at a time. If big data is the elephant, comprehensive link analysis software is part of the one ‘bite’ at a time. Or should we say ‘byte’.
(NOTE: Crime Tech Solutions is an Austin, TX based provider of investigation software and analytics for commercial and law enforcement groups. We proudly support the Association of Certified Fraud Examiners (ACFE), International Association of Chiefs of Police (IACP), Association of Law Enforcement Intelligence Units (LEIU) and International Association of Crime Analysts (IACA). Our offerings include sophisticated link analysis software, an industry-leading investigation case management solution, and criminal intelligence database management systems.)

What is Crime Analysis?

Posted by Tyler Wood Crime Tech Solutions, your source for investigation software.
The information provided on this page comes primarily from Boba, R. (2008: Pages 3 through 6) Crime Analysis with Crime Mapping. For a full discussion of the crime analysis discipline, refer to the book which can be obtained through www.sagepub.com.
Over the past 20 years, many scholars have developed definitions of crime analysis. Although definitions of crime analysis differ in specifics, they share several common components: all agree that crime analysis supports the mission of the police agency, utilizes systematic methods and information, and provides information to a range of audiences. Thus, the following definition of crime analysis is used as the foundation of this initiative:
Crime analysis is the systematic study of crime and disorder problems as well as other police–related issues—including sociodemographic, spatial, and temporal factors—to assist the police in criminal apprehension, crime and disorder reduction, crime prevention, and evaluation.
Clarification of each aspect of this definition helps to demonstrate the various elements of crime analysis. Generally, to study means to inquire into, investigate, examine closely, and/or scrutinize information. Crime analysis, then, is the focused and systematic examination of crime and disorder problems as well as other police-related issues. Crime analysis is not haphazard or anecdotal; rather, it involves the application of social science data collection procedures, analytical methods, and statistical techniques.
More specifically, crime analysis employs both qualitative and quantitative data and methods. Crime analysts use qualitative data and methods when they examine non-numerical data for the purpose of discovering underlying meanings and patterns of relationships. The qualitative methods specific to crime analysis include field research (such as observing characteristics of locations) and content analysis (such as examining police report narratives). Crime analysts use quantitative data and methods when they conduct statistical analysis of numerical or categorical data. Although much of the work in crime analysis is quantitative, crime analysts use simple statistical methods, such as frequencies, percentages, means, and rates. Typical crime analysis tools include link analysis and crime mapping software.
The central focus of crime analysis is the study of crime (e.g., rape, robbery, and burglary); disorder problems (e.g., noise complaints, burglar alarms, and suspicious activity); and information related to the nature of incidents, offenders, and victims or targets of crime (targets refer to inanimate objects, such as buildings or property). Crime analysts also study other police-related operational issues, such as staffing needs and areas of police service. Even though this discipline is called crime analysis, it actually includes much more than just the examination of crime incidents.
Although many different characteristics of crime and disorder are relevant in crime analysis, the three most important kinds of information that crime analysts use are sociodemographic, spatial, and temporal. Sociodemographic information consists of the personal characteristics of individuals and groups, such as sex, race, income, age, and education. On an individual level, crime analysts use sociodemographic information to search for and identify crime suspects. On a broader level, they use such information to determine the characteristics of groups and how they relate to crime. For example, analysts may use sociodemographic information to answer the question, “Is there a white, male suspect, 30 to 35 years of age, with brown hair and brown eyes, to link to a particular robbery?” or “Can demographic characteristics explain why the people in one group are victimized more often than people in another group in a particular area?”
The spatial nature of crime and other police-related issues is central to understanding the nature of a problem. In recent years, improvements in computer technology and the availability of electronic data have facilitated a larger role for spatial analysis in crime analysis. Visual displays of crime locations (maps) and their relationship to other events and geographic features are essential to understanding the nature of crime and disorder. Recent developments in criminological theory have encouraged crime analysts to focus on geographic patterns of crime, by examining situations in which victims and offenders come together in time and space.
Finally, the temporal nature of crime, disorder, and other police-related issues is a major component of crime analysis. Crime analysts conduct several levels of temporal analysis, including (a) examination of long-term patterns in crime trends over several years, the seasonal nature of crime, and patterns by month; (b) examination of mid-length patterns, such as patterns by day of week and time of day; and (c) examination of short-term patterns, such as patterns by day of the week, time of day, or time between incidents within a particular crime series.
The final part of the crime analysis definition—”to assist the police in criminal apprehension, crime and disorder reduction, crime prevention, and evaluation” generally summarizes the purpose and goals of crime analysis. The primary purpose of crime analysis is to support (i.e., “assist”) the operations of a police department. Without police, crime analysis would not exist as it is defined here.
The first goal of crime analysis is to assist in criminal apprehension, given that this is a fundamental goal of the police. For instance, a detective may be investigating a robbery incident in which the perpetrator used a particular modus operandi (i.e., method of the crime). A crime analyst might assist the detective by searching a database of previous robberies for similar cases.
Another fundamental police goal is to prevent crime through methods other than apprehension. Thus, the second goal of crime analysis is to help identify and analyze crime and disorder problems as well as to develop crime prevention responses for those problems. For example, members of a police department may wish to conduct a residential burglary prevention campaign and would like to target their resources in areas with the largest residential burglary problem. A crime analyst can assist by conducting an analysis of residential burglary to examine how, when, and where the burglaries occurred along with which items were stolen. The analyst can then use this information to develop crime prevention suggestions, (such as closing and locking garage doors) for specific areas.
Many of the problems that police deal with or are asked to solve are not criminal in nature; rather, they are related to quality of life and disorder. Some examples include false burglar alarms, loud noise complaints, traffic control, and neighbor disputes. The third goal of crime analysis stems from the police objective to reduce crime and disorder. Crime analysts can assist police with these efforts by researching and analyzing problems such as suspicious activity, noise complaints, code violations, and trespass warnings. This research can provide officers with information they can use to address these issues before they become more serious criminal problems.
The final goal of crime analysis is to help with the evaluation of police efforts by determining the level of success of programs and initiatives implemented to control and prevent crime and disorder and measuring how effectively police organizations are run. In recent years, local police agencies have become increasingly interested in determining the effectiveness of their crime control and prevention programs and initiatives. For example, an evaluation might be conducted to determine the effectiveness of a two-month burglary surveillance or of a crime prevention program that has sought to implement crime prevention through environmental design (CPTED) principles within several apartment communities. Crime analysts also assist police departments in evaluating internal organizational procedures, such as resource allocation (i.e., how officers are assigned to patrol areas), realignment of geographic boundaries, the forecasting of staffing needs, and the development of performance measures. Police agencies keep such procedures under constant scrutiny in order to ensure that the agencies are running effectively.
In summary, the primary objective of crime analysis is to assist the police in reducing and preventing crime and disorder. Present cutting edge policing strategies, such as hotspots policing, problem-oriented policing, disorder policing, intelligence-led policing, and CompStat management strategies, are centered on directing crime prevention and crime reduction responses based on crime analysis results. Although crime analysis is recognized today as important by both the policing and the academic communities, it is a young discipline and is still being developed. Consequently, it is necessary to provide new and experienced crime analysts with training and assistance that improves their skills and provides them examples of best practices from around the country and the world. http://crimetechsolutions.com
 

Policing in my hometown (Winnipeg) gets smart

Posted by Douglas Wood, Crime Tech Solutions
As a native Winnipeg boy, this article in the Winnipeg Sun caught my attention…
1297227913993_ORIGINALThe government of Manitoba, Canada won’t be making good on its 2011 election pledge to put an extra 50 cops on the streets to combat crime and keep Winnipeg neighborhoods safe.

But it’s not because the province is unwilling.  It’s because the city of Winnipeg doesn’t want more cops.
That may seem odd for a city with the highest violent crime rate in the country. But as policing resources shift away from boots on the ground to more crime-analysis based law enforcement, it’s not more sworn officers the Winnipeg Police Service wants, it’s more resources for so-called smart policing strategies.
“The interest of Winnipeg Police Service is not in officers so much as in crime analysis and smart policing and they have a different approach,” Justice Minister Gord Mackintosh told a legislative committee on Monday. “They do not have an interest in just adding more.” The New Democratic Party promised voters during the last provincial election that it would fund 50 additional officers if re-elected. But four years later, the province has only funded 23 more officers. And there won’t be any new funding for more officers, said Mackintosh.
“The commitment was 50 more officers and we’re now at the equivalent of 23,” said Mackintosh. “The city has requested that the election commitment not be implemented as enunciated during the campaign.” It’s a major shift from years past when provincial parties regularly pledged to put more cops on the street by directly funding the Winnipeg Police Service. The former government was the first to make the promise in 1995 when it promised 40 more police officers for Winnipeg.
The province now directly pays for the salaries and benefits of 172 Winnipeg officers, according to a 2014 report.
And while that funding is expected to continue, the city doesn’t want more money for cops. They want it to help fund other aspects of policing, including more preventative measures, said Mackintosh.
“This is a different approach that is gaining momentum not just here in Winnipeg but in other jurisdictions across the continent,” said Mackintosh. “It’s really about hot spot policing now, it’s about data analysis, looking at the types of offences where they occur, the time of day.” Winnipeg police board chairman Coun. Scott Gillingham confirmed the city isn’t looking for more funding to expand the police complement further. He says police are looking to hire more crime analysts, which can be civilians, not more cops.
“The opportunity and the need would be to focus on preventative measures through things like the smart policing initiative (and) intelligence-led policing,” said Gillingham.
What police also need, though, is more help with the additional workload they’ve taken on as they deal increasingly with mental health patients, Child and Family Services cases and soaring domestic abuse calls.
Police may be moving towards a more data-based approach to law enforcement, but they’ve also become a service of last resort for a growing number of tough social service cases, including tracking down chronic runaway wards of the state on a regular basis.
Which means they’re going to need a lot more support from provincial agencies to pick up some of that slack.
Winnipeg police may not need more boots on the ground. After all, Winnipeg does have the most cops per capita of any Canadian city, and has for some time.
But the province is going to have to figure out how to better manage the social service cases that are landing increasingly at the doorstep of police.

What is Link / Social Network Analysis?

Posted by Crime Tech SolutionsPic003

Computer-based link analysis is a set of techniques for exploring associations among large numbers of objects of different types. These methods have proven crucial in assisting human investigators in comprehending complex webs of evidence and drawing conclusions that are not apparent from any single piece of information. These methods are equally useful for creating variables that can be combined with structured data sources to improve automated decision-making processes. Typically, linkage data is modeled as a graph, with nodes representing entities of interest and links representing relationships or transactions. Links and nodes may have attributes specific to the domain. For example, link attributes might indicate the certainty or strength of a relationship, the dollar value of a transaction, or the probability of an infection.

Some linkage data, such as telephone call detail records, may be simple but voluminous, with uniform node and link types and a great deal of regularity. Other data, such as law enforcement data, may be extremely rich and varied, though sparse, with elements possessing many attributes and confidence values that may change over time.
Various techniques are appropriate for distinct problems. For example, heuristic, localized methods might be appropriate for matching known patterns to a network of financial transactions in a criminal investigation. Efficient global search strategies, on the other hand, might be best for finding centrality or severability in a telephone network.
Link analysis can be broken down into two components—link generation, and utilization of the resulting linkage graph.
Link Generation
Link generation is the process of computing the links, link attributes and node attributes. There are several different ways to define links. The different approaches yield very different linkage graphs. A key aspect in defining a link analysis is deciding which representation to use.
Explicit Links
A link may be created between the nodes corresponding to each pair of entities in a transaction. For example, with a call detail record, a link is created between the originating telephone number and the destination telephone number. This is referred to as an explicit link.
Aggregate Links
A single link may be created from multiple transactions. For example, a single link could represent all telephone calls between two parties, and a link attribute might be the number of calls represented. Thus, several explicit links may be collapsed into a single aggregate link.
Inferred Relationships
Links may also be created between pairs of nodes based on inferred strengths of relationships between them. These are sometimes referred to as soft links, association links, or co-occurrence links. Classes of algorithms for these computations include association rules, Bayesian belief networks and context vectors. For example, a link may be created between any pair of nodes whose context vectors lie within a certain radius of one another. Typically, one attribute of such a link is the strength of the relationship it represents. Time is a key feature that offers an opportunity to uncover linkages that might be missed by more typical data analysis approaches. For example, suppose a temporal analysis of wire transfer records indicates that a transfer from account A to person X at one bank is temporally proximate to a transfer from account B to person Y at another bank. This yields an inferred link between accounts A and B. If other aspects of the accounts or transactions are also suspicious, they may be flagged for additional scrutiny for possible money laundering activity.
A specific instance of inferred relationships is identifying two nodes that may actually correspond to the same physical entity, such as a person or an account. Link analysis includes mechanisms for collapsing these to a single node. Typically, the analyst creates rules or selects parameters specifying in which instances to merge nodes in this fashion.
Utilization
Once a linkage graph, including the link and node attributes, has been defined, it can be browsed, searched or used to create variables as inputs to a decision system.
Visualization
In visualizing linking graphs, each node is represented as an icon, and each link is represented as a line or an arrow between two nodes. The node and link attributes may be displayed next to the items or accessed via mouse actions. Different icon types represent different entity types. Similarly, link attributes determine the link representation (line strength, line color, arrowhead, etc.).
Standard graphs include spoke and wheel, peacock, group, hierarchy and mesh. An analytic component of the visualization is the automatic positioning of the nodes on the screen, i.e., the projection of the graph onto a plane. Different algorithms position the nodes based on the strength of the links between nodes or to agglomerate the nodes into groups of the same kind. Once displayed, the user typically has the ability to move nodes, modify node and link attributes, zoom in, collapse, highlight, hide or delete portions of the graph.
Variable Creation
Link analysis can append new fields to existing records or create entirely new data sets for subsequent modeling stages in a decision system. For example, a new variable for a customer might be the total number of email addresses and credit card numbers linked to that customer.
Search
Link analysis query mechanisms include retrieving nodes and links matching specified criteria, such as node and link attributes, as well as search by example to find more nodes that are similar to the specified example node.
A more complex task is similarity search, also called clustering. Here, the objective is to find groups of similar nodes. These may actually be multiple instances of the same physical entity, such as a single individual using multiple accounts in a similar fashion.
Network Analysis
Network analysis is the search for parts of the linkage graph that play particular roles. It is used to build more robust communication networks and to combat organized crime. This exploration revolves around questions such as:

  • Which nodes are key or central to the network?
  • Which links can be severed or strengthened to most effectively impede or enhance the operation of the network?
  • Can the existence of undetected links or nodes be inferred from the known data?
  • Are there similarities in the structure of subparts of the network that can indicate an underlying relationship (e.g., modus operandi)?
  • What are the relevant sub-networks within a much larger network?
  • What data model and level of aggregation best reveal certain types of links and sub-networks?
  • What types of structured groups of entities occur in the data set?

Applications
Link analysis tools such as those provided by Crime Tech Solutions are increasingly used in law enforcement investigations, detecting terrorist threats, fraud detection, detecting money laundering, telecommunications network analysis, classifying web pages, analyzing transportation routes, pharmaceuticals research, epidemiology, detecting nuclear proliferation and a host of other specialized applications. For example, in the case of money laundering, the entities might include people, bank accounts and businesses, and the transactions might include wire transfers, checks and cash deposits. Exploring relationships among these different objects helps expose networks of activity, both legal and illegal.

IBM Crime Analytics: Missing the mark? CTS Hits the bullseye!

quote-one-may-miss-the-mark-by-aiming-too-high-as-too-low-thomas-fuller-10-41-63Posted by Crime Tech Solutions – Your source for analytics in the fight against crime and fraud.
September 7, 2015. IBM announced this week a major update to its IBM i2 Safer Planet intelligence portfolio that includes a major overhaul of the widely used Analyst’s Notebook product. The product, which has become increasingly abandoned by its user base over the past five years, is now being positioned as ‘slicker‘ than previous versions.
IBM suggests that the new version scales from one to 1,000 users and can ingest petabytes of information to visualize. (A single petabyte roughly translates to 20,000,000 four-drawer filing cabinets completely filled with text).
That’s a lot of data. Seems to me that analysts are already inundated with data… now they need more?
This all begs the question: “Where is IBM headed with this product?”
The evidence seems to point to the fact that IBM wants this suite of products to compete head-to-head with money-raising machine and media darling Palantir Technologies. If I’m IBM, that makes sense. Palantir has been eating Big Blue’s lunch for a few years now, particularly at the lucrative US Federal market level. Worse yet, for IBM i2, is the recent news of a new competitor with even more powerful technology.
If I’m a crime or fraud analyst, however, I have to view this as IBM moving further and further away from my reality.
The reality? Nobody has ever yelled “Help! I’ve been robbed. Call the petabytes of ‘slick’ data!”  No, this tiring ‘big data’ discussion is not really part of the day to day work for the vast majority of analysts. Smart people using appropriate data with intuitive and flexible crime technology solutions… that’s the reality for most of us.
So, as IBM moves their market-leading tool higher and higher into the stratosphere, where does the industry turn for more practical desktop solutions with realistic pricing? For more and more customers around the world, the answer is a crime and fraud link analytics tool from Crime Tech Solutions.
No, it won’t ingest 20,000,000 four-drawer filing cabinets of data, and it’s more ‘efficient‘ than ‘slick‘. Still, the product has been around for decades as a strong competitor to Analysts Notebook, and is well-supported by a network of strategic partners around the world. Importantly, it is the only American made and supported alternative. Period. It’s also, seemingly, the last man standing in the market for efficient and cost-effective tools that can be used by real people doing their real jobs.

Is "Minority Report" pure fiction?

Minority-Report-editPosted by Douglas Wood.
Journalist Raj Shekhar had an interesting article in the Times of India this week.
It’s like PreCrime, only four decades early. The “predictive policing” system seen in the Tom Cruise blockbuster Minority Report is now taking shape in Delhi. But instead of the three slime-immersed psychic “Precogs” that system relied on, Delhi Police’s crime prediction will be based on cold, hard data.
Once Enterprise Information Integration Solution or ‘EI2S’—a system that puts petabytes of information from more than a dozen crime databases at police staff’s fingertips—is ready, Delhi Police will be able to implement its ‘Crime Forecast’ plan to predict when and where criminals will strike.
The technology is not as fanciful as it seems at first and is already being tried out in many important cities, including New York, Los Angeles, London and Berlin. Officers associated with the plan say the software will analyze police data for patterns, compare it with other data from jails, courts and other crime-fighting agencies, and alert police to the likely threats. Data will be available not only on the suspects but also their likely victims.
A global tender has been floated for the project and Delhi Police is in talks with various firms for the technology.
According to the article, the system can help pre-empt many situations. For example, a violent clash between two gangs. It can identify individuals who are likely to join gangs or take to crime in an area based on the analyses of their behaviour and network. It can also curb domestic violence by identifying a pattern and predicting the next attack, the article said.
It all boils down to spotting patterns in mountains of data using tremendous computing power. A police document about the plan states that investigators should be able to perform crime series identification, crime trend identification, hot spot analysis and general analysis of criminal profiles. Link analysis will help spot common indicators of a crime by establishing associations and non obvious relationships between entities.
Using neighbourhood analysis, police will be able to understand crime events and the circumstances behind them in a small area as all the crime activity in a neighbourhood will be available for analysis. Criminal cases will be classified into multiple categories to understand what types of crime an area is prone to and the measures needed to curb them. Classification will be done through profiles of victims, suspects, localities and the modus operandi.
Another technique, called proximity analysis, will provide information about criminals, victims, witnesses and other people who are or were within a certain distance of the crime scene. By analyzing demographic and social trends, investigators will be able to understand the changes that have taken place in an area and their impact on criminality.
Network analysis will also be a part of this project to identify the important characteristics and functions of individuals within and outside a network, the network’s strengths and weaknesses and its financial and communication data.
While the system could help fight crime and rid Delhi of its ‘crime capital’ tag, it is bound to raise concerns over privacy and abuse as no predictive system can be foolproof.