Big shoutout to macaquedev and all the people working on the cheater database. Their project has already identified 2,100+ verified cheaters. In my experience, they don't assign a cheater mark easily; some of my reports (which, to me, were clear cases of cheating) were rejected.

Here is a small survey on cheating statistics on Codeforces.

The list of handles of cheaters was taken from the macaquedev GitHub.
Then I used the Codeforces API to gather the rating and the corresponding country of each handle from the list.

Next, I used the Codeforces API to gather the number of active users (rated a contest in the last 6 months) per country.

Rating distribution of caught cheaters

The following graph is a little tricky. We should take into account that relatively higher-rated cheaters cheat more smartly. That is probably one of the reasons why there are not as many cheaters in the blue range as one might expect.

Here is a more detailed table with the percentages: byrange.csv

Demographics of cheaters

Since many people don't list their country on CF, in this section I only take into account users with listed countries. Sadly, we lose more than half of the data here.

I was not satisfied with claims that we see cheaters from region X more often than from other regions simply because there are a lot of participants from region X. To me, this statement is too loose.

How about applying Bayes’ formula? How about computing the conditional probability $$$P[\text{cheater} \mid \text{country X}]$$$?

Let’s make a simple computation:

Here is the problem: I don’t know how to estimate $$$P[\text{cheater}]$$$. Of course, there are many more cheaters than the 2100 listed in the database. So, instead, for each country X we compute the ratio $$$\frac{P[\text{cheater} \mid \text{country X}]}{P[\text{cheater} \mid \text{reference country}]}$$$

Then $$$P[\text{cheater}]$$$ cancels out and we have

As the author of this blog, I choose Russia as the reference country.

Thus, for each country X we need to estimate probabilities $$$P[\text{country X} \mid \text{cheater}]$$$ and $$$P[\text{country X}]$$$.

• cheaters% — % of all identified cheaters who are from the country. It estimates $$$P[\text{country X} \mid \text{cheater}]$$$ and is computed as $$$\frac{\text{number of cheaters from X}}{\text{number of cheaters with identified country}} \cdot 100 $$$.
• users% — % of all identified users who are from the country. It estimates $$$P[\text{country X}]$$$ and is computed as $$$\frac{\text{number of users from X}}{\text{number of users with identified country}} \cdot 100$$$
• rate_vs_ru% — $$$\dfrac{P[\text{cheater} \mid \text{country} X]}{P[\text{cheater} \mid \text{Russia}]} \cdot 100$$$.

Now we can observe the computed values. I drop countries with less than 5 cheaters caught, so that our inference is more stable.