Nimish Doshi's Blog Posts
Nimish is Director, Technical Advisory for Industry Solutions providing strategic, prescriptive, and technical perspectives to Splunk's largest customers, particularly in the Financial Services Industry. He has been an active author of Splunk blog entries and Splunkbase apps for a number of years.
Display Mode
Paginated
Filter
Author
Author URL
Limit
6
The Geometry of Fraud Detection
Splunker Nimish Doshi shares statistical ways to find outliers and visualizes what they would look like if using virtual area or virtual volume as geometric representations to find them.
Zipf's Law and Fraud Detection
Splunker Nimish Doshi breaks down Zipf’s Law to look for possible indicators of fraud.
Benford's Law With Splunk
Use Splunk and Benford's Law to detect fraud by analyzing the first digit distribution of numerical data.
Using Amazon SageMaker to Predict Risk Scores from Splunk
Splunker Nimish Doshi covers using Amazon SageMaker and Splunk to further develop a fraud detection use case to predict future risk scores.
Machine Learning in General, Trade Settlement in Particular
Use the Splunk Machine Learning Toolkit to predict the categorical value of any binary field in an event, and how this approach can be used to predict whether a financial trade will settle before its deadline based on the business semantics of related data.
Improvements to Detecting Modern Financial Crime
This blog provides advice to scale the collection and detection of risk scores that are attributed to Financial Crime rules stored in Splunk.