German Tank Problem

The German Tank Problem was the use of statistical analysis during WW2 to estimate how large the German tank force was during WW2. They did this by sampling serial numbers off captured enemy tanks, then cross referencing those serial number to known factory machinery production rates. The statistical estimate was that the German product 270 tank in February 1944, post war data collected from German logs showed that they actually produced 276. “Conventional” information gathering had the number upwards of 1,000.

The analysis of tank wheels yielded an estimate for the number of wheel molds that were in use. A discussion with British road wheel makers then estimated the number of wheels that could be produced from this many molds, which yielded the number of tanks that were being produced each month. Analysis of wheels from two tanks (32 road wheels each, 64 road wheels total) yielded an estimate of 270 tanks produced in February 1944, substantially more than had previously been suspected.[5]

German records after the war showed production for the month of February 1944 was 276.[6][c] The statistical approach proved to be far more accurate than conventional intelligence methods, and the phrase “German tank problem” became accepted as a descriptor for this type of statistical analysis.


I love this because it’s a form of OSINT, information gathering through open information leakage, and is very relatable to Software Engineering. How many application have you seen where your account is assigned an auto incrementing numeric ID? As an example, [The Grint] does this with their users, and each user has a public profile. My profile ID is 2353828 (2,353,828). Each profile page also shows the date they joined. Using this you can get a solid understanding of how fast The Grint user base grows, and how seasonal new account registration is.


Related Notes