Supplementary Material for
On the Evaluation of Unsupervised Outlier Detection: Measures, Datasets, and an Empirical Study
by G. O. Campos, A. Zimek, J. Sander, R. J. G. B. Campello, B. Micenková, E. Schubert, I. Assent and M. E. Houle
Data Mining and Knowledge Discovery 30(4): 891-927, 2016, DOI: 10.1007/s10618-015-0444-8

Parkinson (5% of outliers version#02)

The data set consists of medical data distinguishing healthy people from those suffering from Parkinson's disease. The latter were labeled as outliers.

Download all data set variants used (278.6 kB). You can also access the original data. (parkinsons.data)

Normalized, without duplicates

This version contains 22 attributes, 50 objects, 2 outliers (4.00%)

Download raw algorithm results (207.4 kB) Download raw algorithm evaluation table (3.6 kB)

Best Parameters

The following table contains the best (overall and per-method) results for each method and evaluation measure (when the same score was achieved twice, only the smallest k is given).
The Maximum F1-Measure is complimentary in addition to the measures in the original publication.

Algorithm k P@n Adj. P@n AP Adj. AP Max-F1 Adj. MF1 ROC AUC
KNN 1 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
KNNW 1 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
LOF 3 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
SimplifiedLOF 4 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
LoOP 4 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
LDOF 8 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
ODIN 11 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
FastABOD 4 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
KDEOS 44 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
LDF 21 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
INFLO 3 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000
COF 5 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000 1.00000

Plots

Precision at n
Adjusted precision at n
Average precision
Adjusted average precision
Maximum F1 score
Adjusted maximum F1 score
ROC AUC
Diversity
A: KNN, B: KNNW, C: LOF, D: SimplifiedLOF, E: LoOP, F: LDOF
G: ODIN, H: KDEOS, I: COF, J: FastABOD, K: LDF, L: INFLO

Not normalized, without duplicates

This version contains 22 attributes, 50 objects, 2 outliers (4.00%)

Download raw algorithm results (208.2 kB) Download raw algorithm evaluation table (12.6 kB)

Best Parameters

The following table contains the best (overall and per-method) results for each method and evaluation measure (when the same score was achieved twice, only the smallest k is given).
The Maximum F1-Measure is complimentary in addition to the measures in the original publication.

Algorithm k P@n Adj. P@n AP Adj. AP Max-F1 Adj. MF1 ROC AUC
KNN 1 0.00000 -0.04167 0.06971 0.03095 0.14286 0.10714 0.59375
KNN 47 0.00000 -0.04167 0.09402 0.05627 0.20000 0.16667 0.70833
KNNW 1 0.00000 -0.04167 0.06381 0.02480 0.14815 0.11265 0.55729
KNNW 2 0.00000 -0.04167 0.06439 0.02541 0.15385 0.11859 0.55208
LOF 1 0.00000 -0.04167 0.09271 0.05490 0.22222 0.18981 0.46875
LOF 4 0.00000 -0.04167 0.10101 0.06355 0.20000 0.16667 0.72917
SimplifiedLOF 1 0.00000 -0.04167 0.06586 0.02694 0.15385 0.11859 0.52604
SimplifiedLOF 6 0.00000 -0.04167 0.11667 0.07986 0.23529 0.20343 0.77083
SimplifiedLOF 7 0.00000 -0.04167 0.11688 0.08009 0.25000 0.21875 0.77083
LoOP 1 0.00000 -0.04167 0.06545 0.02652 0.15385 0.11859 0.52083
LoOP 5 0.00000 -0.04167 0.11667 0.07986 0.23529 0.20343 0.77083
LDOF 2 0.00000 -0.04167 0.09903 0.06149 0.18182 0.14773 0.69792
LDOF 5 0.00000 -0.04167 0.11667 0.07986 0.23529 0.20343 0.77083
LDOF 8 0.00000 -0.04167 0.12500 0.08854 0.22222 0.18981 0.78125
ODIN 1 0.07143 0.03274 0.05612 0.01679 0.12500 0.08854 0.50000
ODIN 30 0.00000 -0.04167 0.09109 0.05322 0.19048 0.15675 0.73438
ODIN 33 0.00000 -0.04167 0.09729 0.05967 0.21053 0.17763 0.72396
FastABOD 3 0.00000 -0.04167 0.06346 0.02444 0.14286 0.10714 0.55208
KDEOS 11 0.00000 -0.04167 0.19091 0.15720 0.30769 0.27885 0.86458
KDEOS 13 0.50000 0.47917 0.31250 0.28385 0.50000 0.47917 0.84375
LDF 1 0.00000 -0.04167 0.09271 0.05490 0.22222 0.18981 0.46875
LDF 21 0.00000 -0.04167 0.15556 0.12037 0.33333 0.30556 0.83333
INFLO 23 0.00000 -0.04167 0.22619 0.19395 0.44444 0.42130 0.89583
INFLO 49 0.51020 0.48980 0.52000 0.50000 0.66667 0.65278 0.75000
COF 1 0.00000 -0.04167 0.06586 0.02694 0.15385 0.11859 0.52604
COF 4 0.00000 -0.04167 0.11212 0.07513 0.23529 0.20343 0.76042
COF 6 0.00000 -0.04167 0.12917 0.09288 0.23529 0.20343 0.79167

Plots

Precision at n
Adjusted precision at n
Average precision
Adjusted average precision
Maximum F1 score
Adjusted maximum F1 score
ROC AUC
Diversity
A: KNN, B: KNNW, C: LOF, D: SimplifiedLOF, E: LoOP, F: LDOF
G: ODIN, H: KDEOS, I: COF, J: FastABOD, K: LDF, L: INFLO