In this note, let’s define analytics as the analysis of data in order to take actions. (This is a narrow definition of analytics, but one that is useful here.) If you don't have day to day work experience with analytics, it is easy to have the mistaken impression that analytics is only about data and statistical models.



Although understanding data and developing statistical models is certainly an important component of an analytic project, this is just one aspect of… Continue

A decision engine framework for real-time deployment of predictive models, ADAPA® supports an extensive collection of statistical and data mining algorithms; overcomes common industry challenges, enabling smart decisions as an integral part of your overall business strategy.



Imagine being able to move a model from the analytics scientist’s desk to a production environment by just moving Predictive Model Markup Language (PMML) files between… Continue

My first blog post..if anyone is interested in what I do..which is internet business consulting then head on over to my blog and check out what I have to offer!

DSGE Model-Based Forecasting of Non-modelled Variables



Frank Schorfheide

Keith Sill

Maxym Kryshko



University of Pennsylvania and Federal Reserve Board of Pennsylvania



ABSTRACT



This paper develops and illustrates a simple method to generate a DSGE model-based forecast for variables that do not explicitly appear in the model (non-core variables). We use auxiliary regressions that resemble measurement equations in a dynamic factor model to…

Continue

An occasional series in which a review of recent posts on SmartData Collective reveals the following nuggets:



First, the decision

The first step is to focus BI and dashboard development on decisions, and this means identifying the decisions that your users must make, the questions to which they need answers, and then focusing on these like a laser. Data quality, data integration, timeliness should all be driven by the decision’s needs. This can be a challenge for… Continue

Forecasting VaR and Expected Shortfall using Dynamical Systems A Risk Management Strategy



Cyril Caillault; Chief Investor Officer, Quantitative Strategies,

Fixed Income and Currencies, Fortis Investments,



Dominique Guégan, PSE – CES-MSE - Université Paris 1 – Panthéon – Sorbonne



Abstract

Using non-parametric and parametric models, we show that the bivariate distribution of an Asian portfolio is not stable along all the period under study. We suggest…

Continue

In their Harvard Business School Press book “Competing on Analytics: The New Science of Winning,” published in February of 2007 Thomas H. Davenport and Jeanne G. Harris discuss three things as the basis of competition: efficient and effective execution, smart decision making, and the ability to wring every drop of value from business processes—all of which can be gained through sophisticated use of analytics. They argue that the frontier for using data to make decisions has shifted… Continue

I was at the Semantic Web Meetup @ the Hearst Building in NYC (amazing venue, the first green building completed in NYC) yesterday and someone asked about open source tools available for data mining, specifically for clustering. Unfortunately I had to run out after the meetup and couldn’t provide these to him. The one mentioned by the presenter was Weka, which also the first free open source tool I came across.



Anyway, here are the ones I have found that are worth checking out and… Continue

THIS QUITE SIMPLY IS A CRUCIAL PAPER IN THE METHODOLOGY OF CREDIT ASSET RISK PRICING



CDO Pricing with Copulae



Barbara Choros

Wolfgang Härdle

Ostap Okhrin



ABSTRACT



Modeling the portfolio credit risk is one of the crucial issues of the last years in the financial problems. We propose the valuation model of Collateralized Debt Obligations based on a one- and two-parameter copula and default intensities estimated from market data. The…

Continue

It's unusual that I see anything from Harvard in my space, if its from Harvard it usually is of interest to my wife! (of which a little more later). But this is interesting allright, more than that its really good;-



The Alchemy of CDO Credit Ratings by Efraim Benmelech (Harvard University and NBER)

Jennifer Dlugosz (Harvard University and Harvard Business School)



ABSTRACT



Collateralized Loan Obligations (CLOs) were one of the largest and fastest growing… Continue

An occasional series in which a review of recent posts on SmartData Collective reveals the following nuggets:



Trend analysis

Trend analysis in a multidimensional environment is simply using time as one of the dimensions that you are slicing and dicing your measures by. If you want to extrapolate from data, albeit in a visual (and possibly non-rigorous manner) to estimate future figures, then often a simple graph will suffice (something that virtually all BI tools will… Continue

If thinking about segmentation, make sure you talk to someone who has actually done a few different types!



There’s another article on consumer segmentation this week that seems to be getting a lot of buzz on twitter etc. You can read the article here in AdAge CMO Strategy section. Michael Fassnacht argues about the weakness of segmentation.



I disagreed with this article and will respond briefly here because I think segmentation studies are the most important type of… Continue

Working with R Community Leaders and Microsoft, REvolution Provides More Memory and Greater Computational Speed, Plus Parallelization for Predictive Analytics Using the R Language

http://www.asymptotix.eu/node/336

Darrell Duffie and Haoxiang Zhu

Stanford University



Abstract



We show whether adding a central clearing counterparty (CCP) for a particular asset class, such as credit derivatives, improves the e±ciency of counterparty risk mitigation and collateral demands, relative to bilateral netting between pairs of dealers. We show that, for plausible cases, adding a CCP for one class of derivatives such as credit default swaps (CDS) can actually reduce netting e±ciency and… Continue

by

Geert Bekaert (Columbia Business School) &

Marie Hoerova and Martin Scheicher (European Central Bank)



EUROPEAN CENTRAL BANK WORKING PAPER SERIES



EXECUTIVE SUMMARY (ABSTRACT)



In this paper, we develop a measure of time-varying risk aversion that is relatively easy to estimate or compute, so that it can be compared to the practitioners’ indices. However, the model we use is inspired by the dynamic asset pricing literature. We view…

Continue

Report prepared by a joint Working Group of

the Financial Stability Forum and the Committee on the Global Financial System



This report explores the link between leverage and valuation in the light of the recent experience of market stress. Prior to the crisis, traditional balance sheet measures of leverage did not give an unambiguous signal of higher risk during the boom years of 2003–07. While balance sheet leverage increased at European banks and US investment banks, and for… Continue

At the High Performance on Wall Street conference (last September (2008)), Microsoft’s high performance computing honcho, Bill Laing announced Windows HPC Server 2008. Microsoft’s goal is to take HPC mainstream and make Windows an alternative to Linux and Unix for HPC customers, particularly in the financial sector.…



Continue

VALUING TOXIC ASSETS: AN ANALYSIS OF CDO EQUITY



Francis A. Longstaff, UCLA Anderson School , and NBER

Brett Myers, Krannert School of Management, Purdue University, and Research Affiliates, LLC



This paper studies this issue from a novel perspective by contrasting the valuation of CDO equity with that of bank stocks. This is possible because both CDO equity and bank stock represent levered first-loss residual claims on an underlying portfolio of debt. There are strong… Continue

by M. Lyra, J. Paha, S. Paterlini, P. Winker

CEFIN – Centro Studi di Banca e Finanza

Dipartimento di Economia Aziendale – Università di Modena e Reggio Emilia



Abstract



Basel II imposes regulatory capital on banks related to the de-fault risk of their credit portfolio. Banks using an internal rating approach compute the regulatory capital from pooled probabilities of default. These pooled probabilities can be calculated by clustering credit borrowers into… Continue

An occasional series in which a review of recent posts on SmartData Collective reveals the following nuggets:



The right feedback

Often today, in our information saturated world, the problem isn't getting feedback, but instead getting feedback in a way that it can be aggregated, managed and responded to in a reasonable fashion. Many of the current methods like email, forums, focus groups and forums simply don't meet the needs effectively. Either the cost is too high, it's… Continue