Societe Generale has been in the news recently and not quite for reasons they would like to be in the news for . In one of the biggest cases of Insider Trading Fraud, an SG employee managed to cause a dent of over $7bn. And this is hardly the first ever case of such use of material non-public information. In one of our earlier posts, we talked about a project where we had built filters to tag suspect insider trades to help our client with identifying potentially suspect trades for manual evaluation. The system has been used retroactively so far, and is being considered for proactive tracking as well.

The efficacy of what we proposed was based on the simplicity of filters that we built. Using tribal knowledge for identifying suspect transactions, and augmenting it with statistical rigor and tests, we were able to generate efficiencies in the compliance/audit process. These same rules can be implemented in a real time fashion to flag suspicious activities for monitoring.

Update: Julie wrote a note to us and pointed out that SoGen case is not a case of insider trading but one of outright fraud. Thank you for catching it and pointing it out to us. Nonetheless, a set of logical and statistics based filters can be a useful part of effective control environment which may have been able to detect such fraudulent activity.

Accurately estimating demand at a granular level is critical for operations management in the travel industry. Traditional estimation models have used historical data to predict the demand. Recently, some companies have started experimenting with a novel source of data to augment the traditional models – the search data from their own websites.
Scandinavian Airlines has been a pioneer in this space.  It is using the volume of search activity on its website for flights on a particular day to estimate demand for the specific routes and flights.  They use this information to guide their operational decisions e.g. which type of aircraft to schedule for the flight segment.  As expected, there was a lot of resistance within the company to make decisions based on these numbers but the web analytics team collaboratively worked with the constituents to gain confidence of the operations team and bring about the change
 Online is already a significant channel in the travel industry.  Web analytics tool vendors like Web Trends and Omniture have made significant inroads and power most of the major travel websites. This means that there is a lot of data readily available for analysis. Travel companies should follow Scandinavian Airline’s lead and start exploring this data to make better operational and marketing decisions.

Investment Banks, with activities encompassing trading as well as deal making, are susceptible to information leakage across activities.  Traders often have access to the material non public information (MNPI) i.e., insider knowledge from the deal makers, which if used can generate significantly higher (illegitimate) profits for the trader or the employer. In recent past, a few traders from leading investment banks have been found guilty of using MNPI and punished. It is beneficial for the banks from a pecuniary as well as reputation point of view to track insider trading activities and take actions against offenders. 

However, it is difficult and resource consuming (financially and intellectually) to manually eyeball millions of trades done by employees and flag potentially fraudulent activity. What may help, though, is a set of robust logical and statistical filters that are designed to reduce the overall number of trades/traders subject to manual review, thus reducing the overall cost of regulatory compliance.

The approach described above requires a non-trivial effort up-front to acquire, aggregate, and clean the trading data. After the required cleaning of trades’ data and imputation of missing value of trades in certain time periods (assuming no trade), we build a general understanding of the traders’ behavior. We supplement this understanding with the help of logical/statistical filters which are a combination of basic measures (such as directionality of trading transactions, means and variances of trade values), trend analysis (such as correlation between trade and market movements, deviation from trader’s historical trading pattern) and statistical models (such as time-series models).

Fig 1: Example of correlation between market movements and trading
action

Fig 2: Example of analyzing directionality of trading actions

Some of the complexities of this approach lie in the inherent biases in any technique that the analytics as well as business teams should be aware of. Whether an OLS model will work as well as a time-series model to identify suspect transactions is a hotly debated question, for instance. The key to this problem, as in most of the advanced analytics
problems, is a strong coordination between business and analytics. Subject matter expertise around investment banking, trading, stock price movements, etc. must be built into a data-driven approach to solving the overall business problem.

Recommendation Engines are being used by many online retailers today to cross-sell and up-sell products and services to online consumers. Amazon.com, Newegg.com, Buy.com seem to use some sophisticated algorithms around the recommendation engines at the heart of their online selling portal. They are also an integral part of any choice optimization strategy.

Without even going to the technicalities of recommendation engines available, we have put together a few points which can help businesses can harness the power of recommendation engines:

• Get the Basics Right
  Understanding some salient features of your products or services can help your business classify and categorize what parameters are important to track and assign weights to and make recommendations to users on. If you are a seller of toys, the most important parameters (with varying weights) may be price, toy features (learning toys or motion-based toys etc.) and toy accessories (batteries, replacement parts etc.). If you sell high-end luxury goods, the most important parameters may not include price and may just center on niche features and custom options.

• Take Baby Steps
  Unless your business is high up on the maturity curve (a la Amazon), you need not start with algorithms that are very sophisticated. Take a baby step approach to developing algorithms. Broadly speaking, recommendation engines can be classified into 3 categories:
1. Content Based filtering engines – those that are based on the contents of an item and tries to pair user interests (if known from previous web visits) to ‘contents’ of an item (can range from books to luxury cars)
2. Collaborating filtering engines or Social filtering engines – those that try to match user profile and interests with other users with similar profile and interests. Takes into account user reviews of products and services.
3. Knowledge-based filtering engines – the most complex of the three, these try to leverage knowledge of user needs and a target product or service that may not be directly related. For example, an engine may try to recommend you a GPS unit based on your interest in books related to Roadtrips or North American geography.
   
   

Ample literature is available on these recommendation engines and other emerging architectures (Few links here). The choice of what recommendation engine is best for the business should be entirely based on the business goals and the products and services being offered.

• Make them Adaptive
  No matter what the nature of the business is, recommendation engines should be built around the belief that there is never a perfect algorithm for designing them. They should be constantly capturing and storing usage data and patterns and must continuously learn from user website visits, time spent on web-pages, third party websites visited and so on. Every time the same user visits your website, the recommendations that are presented will be a little more relevant than on the previous occasion. A sample starting point architecture can be found here.


• Keep it True
  Last but not the least, objectivity of recommendations is valued by the savvy consumer. An online platform for freely expressing opinions (on user experience or product performance) can feed into your recommendation engine to make it better with time. Amazon.com and Buy.com provide not only good platforms for customer feedback but also opinions on where else shoppers can get the same product they are looking at cheaper or costlier rates. The neutrality of the ratings and objectivity of the price positioning influences a customer positively and presents an image that these sellers are not trying to peddle their wares necessarily, but want you to make a good purchase decision as per your needs, preferably through their own stores but not necessarily.


Photo Credits: ieatcrayonz, scott92007, Jmb, losiek