Author: Nikolay Rodionov

Scanning Stock Data for Co-integration Trade Opportunities

by Nikolay Rodionov

Thank God for people like Ben Lambert. I recently got acquainted with the BatchGetSymbols package, an auxiliary library to quantmod, and I am pretty impressed. It’s core function wraps a quality control protocol around quantmod’s getSymbols() function and returns a list with an execution summary and a daily price data datafame. This is a huge … Continue reading Scanning Stock Data for Co-integration Trade Opportunities

DEEP DIVE: Opioids ~ Unsupervised Methods for Kick-back Detection

by Nikolay Rodionov

Alternative Title: How to kill 6 days during Spring Break. The unmasking of the opioids epidemic over the last several years has brought new scrutiny to marketing practices associated with high-risk pharmaceuticals products; Exposé journalistic efforts have been especially effective in shedding light on how misinformation and miscalculations of associated risk factors catalysed a torrent … Continue reading DEEP DIVE: Opioids ~ Unsupervised Methods for Kick-back Detection

SRL NPL for Sanctions Compliance

by Nikolay Rodionov

Here’s a simple question: Why don’t watchlist screening vendors deploy semantic role labeling (SRL) methodologies when screening free-text fields? The value proposition is obvious — analysts would save hours of work each week by not having to clear false-positive alerts like the match of the word “shipped” to “XHAFERI, Shefit” (SDN). But seriously, this is … Continue reading SRL NPL for Sanctions Compliance

Open Payments Data #4: Things to come.

by Nikolay Rodionov

Sorry – no visualizations; Just a quick preview of things I’m hoping to roll out in the next month. I am going to try to do something a little unorthodox: use Rstudio’s Shiny framework to launch data exploration app (ahem!). …Sure, people use Shiny to build dashboards all the time, but the I don’t see … Continue reading Open Payments Data #4: Things to come.

OpenPayments Data #3: Subsidiary Filings Prt. 2

by Nikolay Rodionov

First, some context: The requirement for direct-to-doctor (D2D) marketing transparency was enacted by Physician Payment Sunshine Act as part of ACA reforms in 2010. The call for transparency was initiated in response to concerns that D2D marketing practices by pharmaceutical & medical device companies may exert on undue influence on physician prescription practices. These concerns … Continue reading OpenPayments Data #3: Subsidiary Filings Prt. 2

OpenPayments Data #2: Subsidiary Filings Prt. 1

by Nikolay Rodionov

One the my biggest data-quality frustrations with CMS data is the non-standardization of key fields, which prevents effective aggregation and analysis. The best example of this is the “payer” and “filer” fields. The payor fields Applicable_Manufacturer_or_Applicable_GPO_Making_Payment_ID and Applicable_Manufacturer_or_Applicable_GPO_Making_Payment_Name identify into the pharmaceutical companies making the payments. Although the ‘ID’ field is standardized for the most … Continue reading OpenPayments Data #2: Subsidiary Filings Prt. 1

OpenPayments Data #1: Activity Distributions

by Nikolay Rodionov

I’m finally getting to a point where I can start exploring CMS Open Payments data after a couple months of on-and-off tying in complementary datasets. Spoiler: There’s probably going to be a decent amount of posts following this one on pharmaceutical marketing practices. I’m starting things off with a series of visualizations of how payments … Continue reading OpenPayments Data #1: Activity Distributions

rbindlist() for all of you list-of-dataframe monsters

by Nikolay Rodionov

ALAS! Why is gov’t data so terribly structured?! I’ve been working with the CMS Open Payments data recently because the annual datasets offer enough granular info to allow for good modeling practices and pharmaceutical marketing practices are pretty interesting from a policy stand-point. My only harp with the data is it’s poor data structure and … Continue reading rbindlist() for all of you list-of-dataframe monsters