We strongly believe that there is no "best" algorithm in machine learning. There is only the right tool to apply to a specific dataset. Our process involves determining which combination of algorithms best serves the needs of our clients. We then construct ensembles of these algorithms in Java and deploy them as individual production objects. Depending on the specifics of the dataset, these objects may be based on SVM, RandomForest, or Gradient Boosting among many others. We typically test over 60 approaches before constructing a production ensemble.
Yes and no. We test Deep Learning algorithms such as Reverse Boltzmann Machines and other recurrent networks as part of our testing phase. We have yet to find a financial or genetics dataset that is best classified by these networks versus tree based and SVM approaches. The real strength of Deep Learning lies in unsupervised learning and in vision related areas. As new approaches come to the fore, we will continue to add them to our evaluation scheme.
We work with a form of artificial intelligence known as machine learning. More specifically with supervised learning binary classification systems. These are adaptive systems that continue to "learn" as additional use cases become available. This ongoing learning, without changes in the program code, qualifies this as a form of artificial intelligence. We are not involved in the search for "strong AI" or any form of generalized computer intelligence. (Sorry, science fiction fans.)
In the early days of neural networks, machine learning systems were "black boxes", systems that could not explain the decisions that they reached. We've come a long way since the 1980s. We can tell you exactly why we reached a lending decision and can do so with mathematical accuracy. Our system was designed to be fully compliant with all FCRA regulations from the ground up. Additionally, we specifically exclude from analysis any data that might proxy for a protected class. In our model, we don't know or care about the gender, age, race, religion, zip code, sexual preference, or ethnicity of applicants. We strongly believe that these attributes are fundamentally NOT predictive of credit worthiness.
No. Until there is some concrete evidence that the number of Facebook friends you have is predictive of loan repayment, we'll pass. Social media can be somewhat useful in fraud identification, but before you invest too heavily in this approach you might Google "catfishing". We rely upon third party data sources that validate their data.