Star DJs and mentorship – a social network analysis

Probably most of those who have visited a couple of music festivals have experienced that somehow its always just a handful of stars who are headlining the main stage. In this work, we came after this phenomenon with a particular focus on electronic dance music and top DJs in a data-driven fashion.

Like Comment
Read the paper

We investigated various aspects of success and networking of DJs who have ever made it to the annual Top 100 of the DJ Magazin (, which spans from 1997 to 2018 and contains more than five hundred highly successful DJs and producers. First, we studied the dynamics of the ranking of the Top 100 DJs by statistical tools, and found that there are two distinct domains within the Top 100. DJs who became long-standing stars reaching and staying at the top of the ranking, and DJs with an intrinsically more ephemeral success only touching the lower parts of the ranking.

Next, we constructed the co-release network of the Top 100 DJs and uncovered that the all-time star DJs tend to be parts of separate groups, as we extracted seven distinct communities of the artists. Interestingly, all these communities are centered around one or two former or current No. 1 DJs, implying that the most prominent stars build their own schools. By further analyzing the dynamics of this network, it turned out that the different DJ communities rise, peak, and fall, one after the other. Moreover, the occurrence of new communities come along with the arrival of a future No. 1., and slight but diverging changes in trending genres, showing, for instance, how progressive house gained popularity over techno.

Finally, we investigated a possible driving force responsible for the formation of these observed communities: mentorship. We defined mentorship here in the following way: DJ1 is the mentor of DJ2 if they both made it to the Top 100 ranking respectively at times t1 and t2 (with t1 < t2 ) and if they first appeared on the same release earlier than t2. Following this definition, we found that half of the Top 100 DJs have been mentored before, and the majority of them by all-time stars. Our further results are two-fold: on the one hand, mentored DJs have much higher chances of achieving high ranks, on the other hand, mentored DJs have a very slim chance of becoming all-time stars.

Milan Janosov

PhD in Network Science, Central European University

With a background in physics and biophysics, I earned my PhD in network and data science in 2020. I studied and researched at the Eötvös Loránd University and the Central European University in Budapest, at the Barabási Lab in Boston, and the Bell Labs in Cambridge. Forbes 30u30. NFT sales contributions on SuperRare and Foundation. Alumni at Eötvös Collegium.

I am currently the chief data scientist of Datapolis, a research affiliate at the Central European University, a senior data scientist at Maven7, and a data science expert of the European Commission.

I was awarded the Scholarship of the Republic of Hungary three times, won multiple prizes at science competitions, presented my work in peer-reviewed journals and conferences from Nature's Scientific Reports to MIT. 

My work has been featured in Nature Social Science Research, GQ, Times Higher Education, New Scientist, New York Times, TechXplore, The Economic Times, Futurism,, Nightigale, and more.