Each year, Risk Quant Europe Conference, a conference well-attended by practitioners from banking, asset management, insurers as well as academics from Europe, selects two papers to present in their annual conference.
For 2018, our paper is lucky to be one of the two winning papers selected by the Advisory Board for the conference to be held in London. Please feel free to check out our paper titled CDS Rate Construction Methods by Machine Learning…Continue
Added by Zhongmin Luo on February 24, 2018 at 2:00am — No Comments
Does it sound familiar to you? In order to get an idea of how to choose a parameter for a given classifier, you have to cross reference to a number of papers or books, which often turn out to present competing arguments for or against a certain parameterization choice but with few applications to real-world problems.
For example, you may find a few papers discussing optimal selection of K in…Continue
Cross Validation is often used as a tool for model selection across classifiers. As discussed in detail in the following paper https://ssrn.com/abstract=2967184, Cross Validation is typically performed in the following steps:
In practice, we often have to make parameterization choices for a given classifier in order to achieve optimal classification performances; just to name a few examples:
Added by Zhongmin Luo on May 29, 2017 at 12:49am — No Comments
Past literature show that the comparisons of classifier's performance are specific to the types of datasets (e.g., Pharmaceutical industry data) used; i.e., some classifiers may perform better in some context than others. A paper titled CDS Rate Construction Methods by Machine Learning Techniques conducts the performance comparison exclusively in the context of financial market by applying a wide range of classifiers to provide solution to so-called Shortage of…Continue
Added by Zhongmin Luo on May 23, 2017 at 1:30am — No Comments
Having looked at the fundamentals in the first blog, the natural next step is to understand the various types of strategies to "attack" the data and make it reveal useful information. However, there is one step we must take just before that: Understand the "enemy" i.e. the problem at hand and the data available.
The Tree of the Data Shinobi:
The tree below is an attempt at categorizing the most commonly…Continue
Added by Amogh Borkar on June 8, 2014 at 2:30am — No Comments