Irfan Knows

I really do!

Creating Choice Based Conjoint Manipulations Programmatically with GIMP

I am doing a discrete choice experiment design for a project that we are just starting. The idea is to present screenshots of various app’s in an app store and ask the participants to pick one. For this, we need screenshots of app’s with key variables changed. The problem is that, unless you are careful you may make mistakes in creating manipulations. Especially if there are more than a handful conditions. For this, I used GIMP and xcftools package to programmatically create the treatments.

Continue reading “Creating Choice Based Conjoint Manipulations Programmatically with GIMP”

Finished Last Night on Earth Minis

Tonight I finally finished Last Night on Earth miniatures. I painted the heroes a while back. For a while I was pretty satisfied with the effort. Then I saw Sorastro’s Zombicide painting guide for zombies… Having painted the zombies I thought I was done, but then I saw Consadine’s basic basing guide. Well finally tonight I think I am done for good with LNoE (maybe except for a foam core box insert).

Continue reading “Finished Last Night on Earth Minis”

Foamcore Dice Tower

Azade is old enough to play simple games (Animal upon Animal, Brandon the Brave) but dice throwing has been a problem. A while back I decided to build a dice tower with the dual purpose of both playing games with kids and to make sure the dice is properly random (no cheating). Continue reading “Foamcore Dice Tower”

3D plots in R with Plotly

I was looking to visualize some interactions for our engagement study. I decided to use a 3D plot but the R base plots did not look appealing. I guess ggplot2 pampered me a bit. My search lead me to plotly. Visually pleasing plots with R and Python.

Continue reading “3D plots in R with Plotly”

If you let them build it!

I was in Hawaii last week to present “If You Let Them Build It, They Will Stay! An Empirical Study of Add-on Content and User Engagement”. It was a great honor to see the paper nominated for best paper award, alas we did not receive the award. This is the first paper we released based on the Steam Dataset I have been collecting and I am very excited to see where this dataset will take us.

Continue reading “If you let them build it!”

In Hawaii for HICSS 50. So far so good. Have seen old friends, met new friends and am enjoying Panoply security competition. Paper being nominated as best paper does not hurt either.



Board Games and Miniature Painting

Alright, so far I have been posting about my research and teaching… Now that I have a job that I feel fairly confident about, I think I can actually blog with a bit more liberty. I have been a huge fan of boardgames since I laid my eyes on the “Milyoner” (Turkish knockoff of monopoly). Moving to the US has only broadened my horizons when it comes to board games and now I have a decent collection of my own.

Recently I ascended to a new level in the hobby. I am now painting the miniatures that come with some of my games.  I must admit I am pretty new to the hobby and am not implementing all the tips and tricks a seasoned painter knows. Continue reading “Board Games and Miniature Painting”

c I use AWS to run the various scripts used in data collection.  I have been paying about $20 each month for a t1 micro instance since my free tier and academic credits ran out. That is quite a price to pay for 1 core and about 600MB ram. Maybe AWS is not the best option for long running tasks. The advantages of AWS (fast and easy to deploy) do not matter so much in the long run, and a more traditional hosting option may be more cost effective for those cases.

Still all is not lost, Amazon has been offering reserved instances since 2009. Reserving your instance up front rather than paying for it as you go can add up to significant savings. I recently switched to reserved instances and now my costs are less than 10$ per month for that t1 micro.

Understanding Neural Networks

A few months ago I made a presentation on Tensor Flow for MBA students. The challenge was to simplify the technical underpinnings of the technology sufficiently while preserving a semblance of what it was good for. One particular challenge was visualizing the technology. Showing python code and output was out of the question and at the time TensorBoard was not up to the challenge.

This week I was pleasantly surprised to find A Neural Network Playground. It is a demo of a Neural Network built on top of Tensor Flow. The underlying mechanism is completely abstracted away, so it is more about understanding how a neural network works and less about Tensor Flow.

Continue reading “Understanding Neural Networks”

Blog at

Up ↑