A running, timestamped record of every significant action taken while working with the current dataset — fitting topics, running a K-sweep, embedding, clustering, flagging outliers, adding a group to knowledge, reopening one for further analysis, and so on. Purely observational: it documents the process, it doesn't affect it. Resets whenever you switch datasets.
Process of analysis
1:09:09 PM
1. Loaded dataset
BPI Challenge 2013 — IT incident management (Volvo IT / VINST) — 7,553 traces, 13 activities
1:09:11 PM
2. Added obvious group to knowledge
Accepted_In_Progress → Accepted_In_Progress → Completed_In_Call (1,749 traces)
1:09:15 PM
3. Scored encoding candidates
top recommendation: activities + 2-grams + distinct teams involved + team handoffs + ever in "Wait User" status + starting support line + highest support line reached · n=5,804
1:09:27 PM
4. Ran K-sweep
K=3..20 on the working set
1:09:31 PM
5. Fit topics
K=8 · vocab=105 · relative error=0.4463 · 5,804 traces
1:09:32 PM
6. Fit topics
K=10 · vocab=105 · relative error=0.4034 · 5,804 traces
1:09:34 PM
7. Fit topics
K=12 · vocab=105 · relative error=0.3672 · 5,804 traces
1:09:35 PM
8. Fit topics
K=14 · vocab=105 · relative error=0.3407 · 5,804 traces
1:09:37 PM
9. Fit topics
K=16 · vocab=105 · relative error=0.3184 · 5,804 traces
1:09:39 PM
10. Fit topics
K=18 · vocab=105 · relative error=0.2987 · 5,804 traces
1:09:41 PM
11. Fit topics
K=20 · vocab=105 · relative error=0.2806 · 5,804 traces
1:09:43 PM
12. Fit topics
K=14 · vocab=105 · relative error=0.3407 · 5,804 traces
1:09:48 PM
13. Added topic to knowledge
T1 (K=14) (616 traces)
1:09:48 PM
14. Added topic to knowledge
T6 (K=14) (473 traces)
1:09:49 PM
15. Added topic to knowledge
T9 (K=14) (251 traces)
1:09:50 PM
16. Added topic to knowledge
T13 (K=14) (135 traces)
1:09:54 PM
17. Scored encoding candidates
top recommendation: activities + 2-grams + gap-augmented 2-grams · n=4,329
1:10:15 PM
18. Ran K-sweep
K=3..20 on the working set
1:10:17 PM
19. Fit topics
K=4 · vocab=288 · relative error=0.6537 · 4,329 traces
1:10:18 PM
20. Fit topics
K=6 · vocab=288 · relative error=0.6126 · 4,329 traces
1:10:20 PM
21. Fit topics
K=8 · vocab=288 · relative error=0.5844 · 4,329 traces
1:10:21 PM
22. Fit topics
K=10 · vocab=288 · relative error=0.5620 · 4,329 traces
1:10:23 PM
23. Fit topics
K=12 · vocab=288 · relative error=0.5424 · 4,329 traces
1:10:25 PM
24. Fit topics
K=14 · vocab=288 · relative error=0.5251 · 4,329 traces
1:10:27 PM
25. Fit topics
K=16 · vocab=288 · relative error=0.5077 · 4,329 traces
1:10:28 PM
26. Fit topics
K=4 · vocab=288 · relative error=0.6537 · 4,329 traces
1:10:29 PM
27. Fit topics
K=3 · vocab=288 · relative error=0.6813 · 4,329 traces
1:10:31 PM
28. Fit topics
K=4 · vocab=288 · relative error=0.6537 · 4,329 traces
1:10:32 PM
29. Fit topics
K=5 · vocab=288 · relative error=0.6322 · 4,329 traces
1:10:33 PM
30. Fit topics
K=6 · vocab=288 · relative error=0.6126 · 4,329 traces
1:10:35 PM
31. Fit topics
K=8 · vocab=288 · relative error=0.5844 · 4,329 traces
1:10:36 PM
32. Fit topics
K=10 · vocab=288 · relative error=0.5620 · 4,329 traces
1:10:38 PM
33. Fit topics
K=12 · vocab=288 · relative error=0.5424 · 4,329 traces
1:10:39 PM
34. Fit topics
K=3 · vocab=288 · relative error=0.6813 · 4,329 traces
1:10:40 PM
35. Fit topics
K=2 · vocab=288 · relative error=0.7143 · 4,329 traces
1:10:41 PM
36. Fit topics
K=3 · vocab=288 · relative error=0.6813 · 4,329 traces
1:10:43 PM
37. Fit topics
K=4 · vocab=288 · relative error=0.6537 · 4,329 traces
1:10:44 PM
38. Fit topics
K=5 · vocab=288 · relative error=0.6322 · 4,329 traces
1:10:45 PM
39. Fit topics
K=6 · vocab=288 · relative error=0.6126 · 4,329 traces
1:10:47 PM
40. Fit topics
K=7 · vocab=288 · relative error=0.5976 · 4,329 traces
1:10:48 PM
41. Fit topics
K=8 · vocab=288 · relative error=0.5844 · 4,329 traces
1:10:49 PM
42. Fit topics
K=2 · vocab=288 · relative error=0.7143 · 4,329 traces
1:10:51 PM
43. Fit topics
K=10 · vocab=288 · relative error=0.5620 · 4,329 traces
1:11:00 PM
44. Ran UMAP embedding
nNeighbors=15 · minDist=0.1 · spread=1 · seed=42 · 4,329 points sampled
1:11:01 PM
45. Ran k-means clustering
8 clusters over 4,329 working-set traces
1:11:02 PM
46. Ran k-means clustering
10 clusters over 4,329 working-set traces
1:11:03 PM
47. Ran k-means clustering
12 clusters over 4,329 working-set traces
1:11:04 PM
48. Ran k-means clustering
16 clusters over 4,329 working-set traces
1:11:05 PM
49. Ran k-means clustering
20 clusters over 4,329 working-set traces
1:11:06 PM
50. Ran k-means clustering
24 clusters over 4,329 working-set traces
1:11:07 PM
51. Ran k-means clustering
28 clusters over 4,329 working-set traces
1:11:08 PM
52. Ran k-means clustering
24 clusters over 4,329 working-set traces
1:11:20 PM
53. Added cluster to knowledge
cluster 0, T9-dominant, 76% line_1_only (190 traces)
1:11:21 PM
54. Added cluster to knowledge
cluster 14, T1-dominant, 78% line_1_only (283 traces)
1:11:22 PM
55. Added cluster to knowledge
cluster 19, T5-dominant, 75% line_1_only (248 traces)
1:11:22 PM
56. Added cluster to knowledge
cluster 23, T4-dominant, 76% line_1_only (160 traces)
1:11:25 PM
57. Downloaded groups CSV
9 group(s), 9 currently active
1:11:25 PM
58. Downloaded traces CSV
7,553 traces × 9 group column(s)