Abhinav Unnam

Data Scientist at Curl Analytics

4:57 PM, 9th May 2018

Photofeeler + A/B Testing = Unlocking probable gender bias

It is the mark of a truly intelligent person to be moved by statistics

                                                                    —- George Bernard Shaw

Recently, I had found my self with some off time leaving me with some crazy hypothesis to validate and try out for myself.

One of my experience when soliciting opinions of my pics from friends had an inherent bias in itself. Quite often, my female friends would have a favourable opinion compared to male ones. This led me to investigate if there is an inherent bias in the way a person responds to same gender pictures.

To check and validate for this hypothesis, I used a picture of mine and got it rated from Photofeeler for ratings from the community. The intent was to understand and capture if the hypothesis can be statistically validated.

Photofeeler is a means to get community votes to rate one’s pictures. You could either use earned karma to get votes or buy credits to exchange for votes.

Experimental Design

Null Hypothesis : There is no difference in how different gender are perceiving picture attractive levels.

Alternate Hypothesis : The opposite gender will rate the picture’s attractive levels higher.

  • Male group sample size : 23
  • Female group sample size : 20
  • Parameter under investigation : Attractive 
  • Significance Test : Fisher exact test (small sample sizes , the underlying distribution is normal as well)



There is definitely some merit in how I’m being rated here. To further cement and keep the statistician in myself, calm. I checked for one tail t-test (Fisher Exact).

The corresponding p-value is not significant enough. I guess, the sample size is too small. A repetition of the test with larger sample size would have enough power to probably reject the null hypothesis. As of now, there is no in statistically significant inherent bias as I pre-assumed.

Looking forward to hearing from other people who might wanna try or  had tried this particular experiment. Let me know what the results turn out to be.


Push pixels...
Shovel coal into server...
Create mockups...
Defend the wall...
Draft storyboard...
Disrupt an industry...
Achieve profitability...
Become a unicorn...
Become Batman...