Archives for Chris Stucchio

Thu 29 December 2022
Boosting as a scheme for transfer learning
Tue 07 July 2020
Calibrating a classifier when the base rate changes
Wed 17 June 2020
Shareholder Short-Termism Theory has Died of COVID-19
Tue 24 March 2020
Scalably Detecting Odd-looking Histograms
Tue 10 March 2020
Isotonic: A Python package for doing fancier versions of isotonic regression
Tue 03 March 2020
Cost Matters: Why Lambda School should have a lower success rate than college
Thu 09 January 2020
Notes on setting up a Data Science app on Azure
Mon 09 December 2019
Backtest your SQL queries - they are models too
Thu 25 July 2019
The Final Stage of Grief (about bad data) is Acceptance
Mon 06 May 2019
Don't believe the hype: Basic Income reduces labor supply by 10%, which is a lot
Thu 21 March 2019
Is white nationalism a serious problem? Extracting wikipedia data with Python.
Mon 21 January 2019
Barometric Pressure, a statistical myth: Why one common argument against IQ is flawed
Tue 30 October 2018
AI Ethics, Impossibility Theorems and Tradeoffs
Wed 22 August 2018
Why you can't have privacy on the internet
Mon 30 July 2018
Bayesian Linear Regression and Generalized Linear Models
Tue 20 March 2018
Deterministic A/B tests via the hashing trick
Fri 09 February 2018
Low Rate Loans for Ladies, Stags Pay Extra - The Role of Ethics in AI/ML
Tue 07 November 2017
Why Indian companies should take on different projects than competing Valley companies - an application of Cobb-Douglas
Fri 01 September 2017
Inferring data loss (and correcting for it) from fundamental relationships
Wed 30 August 2017
A.I. 'Bias' Doesn't Mean What Journalists Say It Means
Thu 20 April 2017
Why I'm bullish on Uber - the customer acquisition trough
Mon 27 March 2017
How to Change your Opinion with Python and Bayes Rule
Thu 09 February 2017
Bayesian Linear Regression (in PyMC) - a different way to think about regression
Wed 21 December 2016
Assorted links
Tue 29 November 2016
Respecting Boundaries with Inhomogeneous Kernels
Thu 22 September 2016
Assorted links
Mon 05 September 2016
The Probability Monad and Why it's Important for Data Science
Fri 12 August 2016
Assorted links
Thu 11 August 2016
Measuring Bernoulli Probabilities in the Presence of Delayed Reactions
Thu 16 June 2016
Why Can't Gay Men Donate Blood? A Bayesian Analysis
Mon 30 May 2016
Concurrent bloom filters
Mon 30 May 2016
Assorted links
Tue 24 May 2016
How to lie without statistics - ProPublica edition
Tue 10 May 2016
Robots didn't take our jobs
Thu 14 April 2016
Assorted links
Mon 21 March 2016
Alien Intelligences and discriminatory algorithms
Mon 14 March 2016
Has your conversion rate changed? An introduction to Bayesian timeseries analysis with Python.
Tue 16 February 2016
Assorted links
Mon 15 February 2016
Free objects - a generalized interpreter pattern
Mon 11 January 2016
Bayesian Calibration of a Mobile Phone Compass
Mon 21 December 2015
Assorted links
Mon 14 December 2015
My adventures in medical tourism
Tue 01 December 2015
The Autodidact Ratio: A Better Way to Measure Bias Against Women
Mon 16 November 2015
Assorted links
Thu 05 November 2015
The Mathematics of Paul Graham's Bias Test
Mon 02 November 2015
Multiple Comparisons - Make your boss happy with false positives, guaranteed!
Mon 12 October 2015
Bayesian A/B Testing - my talk at Gilt
Tue 06 October 2015
Testing for Truth vs Maximizing Revenue
Thu 01 October 2015
Wingify releases Bayesian A/B tester
Thu 01 October 2015
Assorted links
Thu 27 August 2015
Assorted links
Fri 24 July 2015
Assorted links
Mon 06 July 2015
Preventing DB sharding errors at compile time with dependent types
Mon 22 June 2015
Assorted links
Mon 22 June 2015
Free Monads in Scalaz - how to use them
Tue 09 June 2015
How to use Apache Thrift (Java version) from Scala
Wed 01 April 2015
Assorted links - lots of excitement edition
Fri 06 February 2015
Assorted links - nothing interesting happened lately edition
Thu 05 February 2015
Constant Rebalanced Portfolios - some simulations with numpy
Thu 29 January 2015
No Free Samples - Counting Tricks won't get you to Statistical Significance
Tue 27 January 2015
Don't use Bandit Algorithms - they probably won't work for you
Tue 20 January 2015
Assorted links
Tue 20 January 2015
One tailed vs two tailed A/B tests - your decision procedure is the deciding factor
Tue 13 January 2015
Uber haters should check their privilege
Mon 05 January 2015
Segmenting your traffic? You are probably doing it wrong.
Mon 15 December 2014
Why my blog is now HTTPS, and why yours should be too
Thu 11 December 2014
Assorted links
Wed 03 December 2014
Type-safe vector addition with Dependent Types
Wed 12 November 2014
Assorted links
Tue 11 November 2014
Deploying Julia Servers with Docker
Mon 03 November 2014
This blog is now https
Sat 01 November 2014
Python LRU Cache version 0.1.1 released
Mon 27 October 2014
Book reviews - stuck in the hospital edition
Sun 26 October 2014
Assorted links
Mon 13 October 2014
Assorted links
Wed 01 October 2014
Computers are made of metal, not category theory
Sat 27 September 2014
Assorted links
Thu 25 September 2014
How many hours of work is optimal? A Python Optimization tutorial
Wed 17 September 2014
Attribution Theory is Misguided
Mon 15 September 2014
Assorted links
Mon 15 September 2014
Scalaz Stream - a Functional Reactive Programming Tutorial
Sun 14 September 2014
The Complexity Copout
Fri 05 September 2014
Why reject complex theories? On the limits of falsifiability
Wed 03 September 2014
Traction Book Giveaway
Tue 26 August 2014
Microservices for the Grumpy Neckbeard
Wed 20 August 2014
Go Read Gabriel Weinberg's "Traction Book" right now
Mon 18 August 2014
Assorted links
Mon 18 August 2014
Existence does not imply correlation (or causation)
Sat 16 August 2014
Spaced Repetition is Awesome: Two App Recommendations
Mon 04 August 2014
Bounded Rationality and the Ellsberg Paradox
Wed 23 July 2014
Assorted links
Tue 08 July 2014
Topology of decisionmaking - are you secretly managing by metric?
Tue 08 July 2014
Assorted links
Fri 04 July 2014
Costrong Comonads are Boring
Sat 28 June 2014
How to return an array of generic type, or "cannot find class tag for element type T"
Wed 25 June 2014
Why a pro/con list is 75% as good as your fancy machine learning algorithm
Wed 25 June 2014
Assorted links
Mon 09 June 2014
Asymptotics of Evan Miller's Bayesian A/B formula
Thu 05 June 2014
Easy Evaluation of Decision Rules in Bayesian A/B testing
Thu 05 June 2014
Assorted links
Mon 19 May 2014
Optimizing Ad Placement with Julia and Maximum Likelihood
Sat 17 May 2014
Mosh - ssh for a bad connection
Thu 15 May 2014
Assorted links
Wed 30 April 2014
Piketty's r > g thesis proves nothing about inequality
Tue 29 April 2014
Assorted links
Sat 26 April 2014
Scala error 'multiple overloaded alternatives of constructor RandomAccessFile define default arguments.'
Tue 22 April 2014
High Frequency Trader's 'Quote Stuffing' is a Software Bug
Mon 21 April 2014
Assorted links
Mon 21 April 2014
Piketty, inequality and volatility: How can r > g?
Sun 13 April 2014
Number Crunching in Scala - my talk at the Pune Scala Symposium
Wed 09 April 2014
Mark Cuban's HFT Idiocy
Mon 07 April 2014
A Fervent Defense of Front-running HFTs
Thu 03 April 2014
How to not get ripped off by High Frequency Traders
Tue 18 March 2014
Assorted links
Tue 18 March 2014
Computerized Eye Exams
Thu 13 March 2014
Why xkcd-style graphs are important
Mon 10 March 2014
I don't understand JVM performance
Mon 03 March 2014
Bandit Algorithm and A/B Testing Tutorial
Tue 25 February 2014
Agents - a purely functional alternative to Actors
Mon 24 February 2014
The Adversarial Bandit is not a Statistics Problem
Thu 20 February 2014
What is the correct price for a (crypto or other) currency?
Tue 18 February 2014
Assorted links
Fri 07 February 2014
Assorted links
Mon 03 February 2014
Mainframe computers
Sat 25 January 2014
Excellent paper on Income Mobility
Thu 23 January 2014
Logback error 'java.lang.ClassNotFoundException: org.codehaus.janino.ScriptEvaluator'
Tue 21 January 2014
Assorted links
Sun 19 January 2014
Handle Failure with MonadPlus/ApplicativePlus
Fri 17 January 2014
The poor don't work because they are economically rational - redux
Fri 17 January 2014
Assorted links
Mon 13 January 2014
Statistical Mechanics has failed the market test or Noah Smith misses the point
Thu 09 January 2014
Learning spire - Scala is Slow, cfor helps
Wed 08 January 2014
Assorted links
Sat 04 January 2014
Spray error "could not find implicit value for evidence parameter of type spray.httpx.marshalling.Marshaller[scala.concurrent.Future[_]]"
Thu 26 December 2013
Assorted links - Eggs Edition
Mon 23 December 2013
Assorted links
Sat 07 December 2013
Learning Spire - Vector Spaces!
Thu 05 December 2013
Learning Spire - Boolean Algebras are pretty cool
Mon 02 December 2013
Don't use Actors for concurrency
Fri 29 November 2013
Scala Patterns - HasXIsX
Fri 22 November 2013
Assorted links
Thu 21 November 2013
How to measure a changing conversion rate (with python code)
Mon 18 November 2013
Assorted links
Thu 14 November 2013
Models help you understand why you disagree
Wed 13 November 2013
Modelling a Basic Income with Python and Monte Carlo Simulation
Thu 07 November 2013
Postgres NOTIFY for cache busting and more
Thu 26 September 2013
Compound Aggregates in Hadoop/Scalding
Mon 16 September 2013
Don't use Hadoop - your data isn't that big
Fri 13 September 2013
java.lang.OutOfMemoryError, GC overhead limit exceeded
Wed 31 July 2013
Mechanical Turk and Error Correcting Codes
Mon 08 July 2013
Bayesian Bandits - optimizing click throughs with statistics
Tue 02 July 2013
Why Not Python - the GIL hinders concurrency
Tue 11 June 2013
Monads are like a dildo factory, staffed by midgets
Sat 01 June 2013
Caching the Identity for Fun and Profit
Mon 20 May 2013
Analyzing conversion rates with Bayes Rule (Bayesian statistics tutorial)
Mon 08 April 2013
The magic of conjugate priors (for online learning)
Tue 05 February 2013
The Metrics Manifesto - Why you need an objective function
Sun 25 November 2012
Write Queries with Tiramisu
Sun 05 August 2012
Flash Crash? Or Flash in the Pan?
Wed 01 August 2012
What I'm reading - How Quantum Mechanics Should be Taught
Mon 16 July 2012
Minimize your cloud costs with GLPK and Haskell
Fri 22 June 2012
Proposal - bigger ticks, more rent seeking
Sun 03 June 2012
Why Multi-armed Bandit algorithms are superior to A/B testing
Mon 28 May 2012
Human vs Machine Progress
Sat 26 May 2012
Don't use Scatterplots
Fri 25 May 2012
Subpenny rule elimination - roundup
Tue 22 May 2012
High Frequency Trading - What's broken and how to fix it
Sat 12 May 2012
Why I ask 'how many golf balls fit on a bus?' on job interviews
Tue 08 May 2012
Unemployment and market clearing
Wed 25 April 2012
A High Frequency Trader's Apology, Pt 2
Tue 24 April 2012
Idli - a command line interface to your bugtracker
Mon 16 April 2012
A High Frequency Trader's Apology, Pt 1
Sat 07 April 2012
In-app caching - spend a little RAM to speed up your site
Fri 06 April 2012
One Hiring Filter that Works
Sun 01 April 2012
How to leave academia
Sat 31 March 2012
Introducing Hobo
Mon 12 December 2011
A simple trick to speed up complex Postgres queries on EC2
Sat 03 December 2011
Networking problems while cloning Ubuntu VM
Mon 28 November 2011
The Calories In/Calories Out model explains weight stability
Sat 19 November 2011
TechCrunch messes up the math on sexism
Fri 18 November 2011
Why Americans don't hire servants
Sat 24 September 2011
Did immigrants (and Simpson's Paradox) cause the Great Stagnation?
Fri 05 August 2011
MapReduce explained in 41 words
Thu 12 May 2011
The poor don't work because they are economically rational
Sat 23 April 2011
The High-Heel Bubble never popped, and the Education Bubble may not either
Tue 12 April 2011
NullPointerException when running distcp to Amazon s3 filesystem
Thu 31 March 2011
Investment, employment, and the role of women
Fri 25 March 2011
Hadoop's MapWritable sometimes a performance hog
Mon 21 February 2011
Structural Shift in the Economy
Sun 20 February 2011
Hadoop error - HTTP Response Code 503
Sun 02 January 2011
Inanity of overeating - don't ignore the bacon in the room