I am interested in reading more about O-Cluster and unfortunately all the links I found only contain very small description of the algorithm and do not give details about how to implement it.

The most detailed link I found is this https://docs.oracle.com/cd/B28359_01/datamine.111/b28129/algo_oc.htm#DMCON059

I need to write a detailed description of the algorithm until tomorrow and I am really stuck

  • Maybe better to ask at softwareengineering.stackexchange.com (but then remove it here)? – user4293 Dec 21 '16 at 9:19
  • Did you search Oracle support forums? They may not be indexed by search engines. – user4293 Dec 21 '16 at 15:18
  • @JanDoggen I will try it out of curiosity. However the professor allowed me to present a different algorithm so I solved the initial problem :) – yoyo_fun Dec 21 '16 at 17:51
  • I'm closing this question because the poster said the task is no longer needed, and also I find it off-topic. – philshem Dec 29 '16 at 10:31

There is a cited reference paper in the link you provide

Campos, M.M., Milenova, B.L.
"O-Cluster: Scalable Clustering of Large High Dimensional Data Sets"

Unfortunately, the paper is behind a paywall and the link from Oracle goes to linkrot. I checked a few dates on the wayback machine and they also are no good.

Perhaps of interest, this algorithm is also implemented in R-Stats

  • In the PDF reference manual you may find more technical details about the algorithm.
| improve this answer | |

Not the answer you're looking for? Browse other questions tagged or ask your own question.