Skip to main content

GRNN with Small Samples

[This article was first published on S+/R – Yet Another Blog in Statistical Computing, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

After a bank launches a new product or acquires a new portfolio, the risk modeling team would often be faced with a challenge of how to estimate the corresponding performance, e.g. risk or loss, with a limited number of data points conditional on business drivers or macro-economic indicators. For instance, it is required to project the 9-quarter loss in CCAR, regardless of the portfolio age. In such cases, the prevalent practice based upon conventional regression models might not be applicable given the requirement for a sufficient number of samples in order to draw the statistical inference. As a result, we would have to rely on the input of SME (Subject Matter Expert), to gauge the performance based on similar products and portfolios, or to fall back on simple statistical metrics such as Average or Median that can’t be intuitively related to predictors.

With the GRNN implemented in the YAGeR project (https://github.com/statcompute/yager), it is however technically feasible to project the expected performance conditional on predictors due to the fact that the projected Y_i of a future case is determined by the distance between the predictor vector X_i and each X vector in the training sample, subject to a smoothing parameter namely Sigma. While more samples in the training data are certainly helpful to estimate a generalizable model, a couple data points, e.g. even only one or two data points in the extreme case, are also conceptually sufficient to form a GRNN that is able to generate sensible projections without violating statistical assumptions.

Following are a couple practical considerations.

  1. Although normalizing the input data, e.g. X matrix, in a GRNN is usually necessary for the numerical reason, the exact scaling is not required. Practically, the “rough” scaling can be employed and ranges or variances used in the normalization can be based upon the historical data of X that might not be reflected in the training data with only a small sample size.
  2. With limited data points in the training data, the Sigma value can be chosen by the L-O-O (Leave-One-Out) or empirically based upon another GRNN with a similar data structure that might or might not be related to the training data. What’s more, it is easy enough to dynamically fine-tune or refresh the Sigma value with more data samples becoming available along the time.
  3. While there is no requirement for the variable selection in a GRNN, the model developer does have the flexibility of judgmentally choosing predictors based upon the prior information and eliminating variables not showing correct marginal effects in PDP (https://statcompute.wordpress.com/2019/10/19/partial-dependence-plot-pdp-of-grnn).

Below is an example of using 100 data points as the training sample to predict LGD within the unity interval of 1,000 cases with both GLM and GRNN. Out of 100 trials, while the GLM only outperformed the simple average for 32 times, the GRNN was able to do better for 76 times.

To leave a comment for the author, please follow the link and comment on their blog: S+/R – Yet Another Blog in Statistical Computing.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.


from R-bloggers https://ift.tt/33wLYuG
via IFTTT
Labels:

Comments

Post a Comment

Popular posts from this blog

Solving Van der Pol equation with ivp_solve

Van der Pol’s differential equation is The equation describes a system with nonlinear damping, the degree of damping given by μ. If μ = 0 the system is linear and undamped, but for positive μ the system is nonlinear and damped. We will plot the phase portrait for the solution to Van der Pol’s equation in Python using SciPy’s new ODE solver ivp_solve . The function ivp_solve does not solve second-order systems of equations directly. It solves systems of first-order equations, but a second-order differential equation can be recast as a pair of first-order equations by introducing the first derivative as a new variable. Since y is the derivative of x , the phase portrait is just the plot of ( x , y ). If μ = 0, we have a simple harmonic oscillator and the phase portrait is simply a circle. For larger values of μ the solutions enter limiting cycles, but the cycles are more complicated than just circles. Here’s the Python code that made the plot. from scipy import linspace from ...
Post a Comment
Read more

Explaining models with Triplot, part 1

[This article was first published on R in ResponsibleML on Medium , and kindly contributed to R-bloggers ]. (You can report issue about the content on this page here ) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. Explaining models with triplot, part 1 tl;dr Explaining black box models built on correlated features may prove difficult and provide misleading results. R package triplot , part of the DrWhy.AI project, is aiming at facilitating the process of explaining the importance of the whole group of variables, thus solving the problem of correlated features. Calculating the importance of explanatory variables is one of the main tasks of explainable artificial intelligence (XAI). There are a lot of tools at our disposal that helps us with that, like Feature Importance or Shapley values, to name a few. All these methods calculate individual feature importance for each variable separately. The problem arises when features used ...
Post a Comment
Read more