Detecting illegal shipments in the global timber trade poses a massive challenge to enforcement agencies. The massive volume and complexity of timber shipments and obfuscations within international trade data, intentional or not, necessitates an automated system to aid in detecting specific shipments that potentially contain illegally harvested wood. To address these requirements we build a novel human-in-the-loop visual analytics system called TIMBERSLEUTH. TimberSleuth uses a novel scoring model reinforced through human feedback to improve upon the relevance of the results of the system while using an off-the-shelf anomaly detection model. Detailed evaluation is performed using real data with synthetic anomalies to test the machine intelligence that drives the system. We design interactive visualizations to enable analysis of pertinent details of anomalous trade records so that analysts can determine if a record is relevant and provide iterative feedback. This feedback is utilized by the machine learning model to improve the precision of the output.
AlmondRGrootenMPetersonT. Living planet Report 2020-Bending the curve of biodiversity loss. World Wildlife Fund, https://bit.ly/wwfReportLPR (2020, accessed 1 March 2022).
6.
RobinsonJESinovasP.Challenges of analyzing the global trade in CITES-listed wildlife. Conserv Biol2018; 32(5): 1203–1206.
EndertARibarskyWTurkayC, et al. The state of the art in integrating machine learning into visual analytics. Comput Graph Forum2017; 36: 458–486.
9.
JiangLLiuSChenC.Recent research advances on interactive machine learning. J Visual2019; 22(2): 401–417.
10.
ThomDBoschHKochS, et al. Spatiotemporal anomaly detection through visual analysis of geolocated Twitter messages. In: Proceedings of the IEEE pacific visualization symposium, 2012, pp 41–48. New York: IEEE. DOI: 10.1109/PacificVis.2012.6183572.
11.
CaoNShiCLinS, et al. Targetvue: visual analysis of anomalous user behaviors in online communication systems. IEEE Trans Vis Comput Graph2016; 22(1): 280–289. 0.
12.
CaoNLinCZhuQ, et al. Voila: visual anomaly detection and monitoring with streaming spatiotemporal data. IEEE Trans Vis Comput Graph2018; 24(1): 23–33. 0.
13.
CaoNLinYRGotzD, et al. Z-glyph: visualizing outliers in multivariate data. Inf Vis2018; 17(1): 22–40.
14.
GoodallJRaganESteedC, et al. Situ: identifying and explaining suspicious behavior in networks. IEEE Trans Visual Comput Graphics2018; 250(1): 204–214. DOI: 10.1109/TVCG.2018.2865029.
15.
XieCXuWMuellerK.A visual analytics framework for the detection of anomalous call stack trees in high performance computing applications. IEEE Trans Vis Comput Graph2019; 25(1): 215–224.
16.
WilkinsonL.Visualizing big data outliers through distributed aggregation. IEEE Trans Vis Comput Graph2018; 24(1): 256–266.
17.
KoSAfzalSWaltonS, et al. Analyzing high-dimensional multivariate network links with integrated anomaly detection, highlighting and exploration. In: Proceedings of the IEEE conference on visual analytics science and technology, 2014, pp. 83–92. New York: IEEE. DOI: 10.1109/VAST.2014.7042484.
18.
ChenCYuanJLuY, et al. Oodanalyzer: interactive analysis of out-of-distribution samples. IEEE Trans Vis Comput Graph2021; 27: 3335–3349.
19.
PerinCDragicevicPFeketeJD.Revisiting bertin matrices: new interactions for crafting tabular visualizations. IEEE Trans Vis Comput Graph2014; 20(12): 2082–2091.
20.
LexAGehlenborgNStrobeltH, et al. Upset: visualization of intersecting sets. IEEE Trans Vis Comput Graph2014; 20(12): 1983–1992.
21.
LexASchulzHJStreitM, et al. Visbricks: multiform visualization of large, inhomogeneous data. IEEE Trans Vis Comput Graph2011; 17(12): 2291–2300.
22.
YalcinMAElmqvistNBedersonBB.Keshif: rapid and expressive tabular data exploration for novices. IEEE Trans Vis Comput Graph2018; 24(8): 2339–2352.
23.
BlumenscheinMBehrischMSchmidS, et al. SMARTexplore: simplifying high-dimensional data analysis through a table-based visual analytics approach. In: Proceedings of the IEEE conference on visual analytics science and technology, 2018, pp. 36–47. New York: IEEE. DOI: 10.1109/VAST.2018.8802486.
24.
FurmanovaKGratzlSStitzH, et al. Taggle: combining overview and details in tabular data visualizations. Inf Vis2020; 19(2): 114–136.
25.
NorthCShneidermanB. Snap-together visualization: a user interface for coordinating visualizations via relational schemata. In: Proceedings of the ACM conference on advanced visual interfaces, 2000, pp 128–135, New York: ACM. DOI: 10.1145/345513.345282.
26.
WeaverC.Building highly-coordinated visualizations in Improvise. In: IEEE symposium on information visualization, 2004, pp. 159–166. New York: IEEE. DOI: 10.1109/INFVIS.2004.12.
27.
PellegDMooreA. Active learning for anomaly and rare-category detection. In: Proceedings of the international conference on neural information processing systems, 2004, pp. 1073–1080, Cambridge, MA: MIT Press.
28.
AbeNZadroznyBLangfordJ.Outlier detection by active learning. In: Proceedings of the ACM SIGKDD conference on knowledge discovery and data mining, 2006. New York, NY: ACM. DOI: 10.1145/1150402.1150459.
29.
HeJCarbonellJ. Nearest-neighbor-based active learning for rare category detection. In: Proceedings of the international conference on neural information processing systems, 2007, pp. 633–640. Neural Information Processing Systems Foundation.
30.
GhaniRKumarM. Interactive learning for efficiently detecting errors in insurance claims. In: Proceedings of the ACM SIGKDD conference on knowledge discovery and data mining, 2011, pp. 325–333, New York: ACM. DOI: 10.1145/2020408.2020463.
31.
VeeramachaneniKArnaldoIKorrapatiV, et al. AI^2: Training a big data machine to defend. In: Proceedings of the IEEE conference on big data security on Cloud, 2016, pp. 49–54. New York: IEEE. DOI: 10.1109/BigDataSecurity-HPSC-IDS.2016.79.
32.
DasSWongWDietterichT, et al. Incorporating expert feedback into active anomaly discovery. In: Proceedings of the IEEE international conference on data mining, 2016, pp. 853–858. New York: IEEE. DOI: 10.1109/ICDM.2016.0102.
33.
PevnýT.Loda: lightweight on-line detector of anomalies. Mach Learn2015; 102: 275–304.
34.
DasSWongWFernA, et al. Incorporating feedback into tree-based anomaly detection. arXiv preprint arXiv:1708.09441, 2017.
35.
SiddiquiMFernADietterichTG, et al. Feedback-guided anomaly discovery via online optimization. In: Proceedings of the ACM conference on knowledge discovery & data mining, 2018, pp. 2200–2209. New York: ACM. DOI: 10.1145/3219819.3220083.
36.
DasSDoppaJ.Glad: Glocalized anomaly detection via active feature space suppression. arXiv preprint arXiv:1810.01403, 2018.
37.
LambaHAkogluL.Learning on-the-job to re-rank anomalies from top-1 feedback. In Proceedings of the international conference on data mining, 2019, pp. 612–620. Philadelphia: SIAM.
38.
KongLChenLChenM, et al. Improve black-box sequential anomaly detector relevancy with limited user feedback. ICML Workshop on Human in the Loop Learning, 2020. International Conference on Machine Learning.
DasKSchneiderJ.Detecting anomalous records in categorical datasets. In: Proceedings of the ACM SIGKD DConference on knowledge discovery and data mining, 2007, pp. 220–229. New York: ACM. DOI: 10.1145/1281192.1281219.
41.
WiedenhoeftACSimeoneJSmithA, et al. Fraud and misrepresentation in retail forest products exceeds US forensic wood science capacity. PLoS One2019; 14(7): e0219917.
42.
ShneidermanB.Human-centered AI. New York: Oxford University Press, 2022.
KarPNarasimhanHJainP. Surrogate functions for maximizing precision at the top. In: International conference on machine learning, 2015, pp. 189–198. Lille: PMLR.
45.
SunYHanJYanX, et al. Pathsim: meta path-based top-k similarity search in heterogeneous information networks. Proc VLDB Endowment2011; 4(11): 992–1003.
46.
CaoBMaoMViiduS, et al. Collective fraud detection capturing inter-transaction dependency. In: Proceedings of the KDD workshop on anomaly detection in finance, 2018, pp. 66–75. New York: ACM.
47.
CaoBMaoMViiduS, et al. Hitfraud: a broad learning approach for collective fraud detection in heterogeneous information networks. In: Proceedings of the IEEE international conference on data mining, 2017, pp. 769–774. New York: IEEE, 2017. DOI: 10.1109/ICDM.2017.90.
48.
DattaDIslamMSelfN, et al. Detecting suspicious timber trades. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, 2020, pp. 13248–13254. DOI: 10.1609/aaai.v34i08.7032.
49.
AkogluLTongHVreekenJ, et al. Fast and reliable anomaly detection in categorical data. In: Proceedings of the ACM conference on information and knowledge management, pp. 415–424, 2012. DOI: 10.1145/2396761.2396816.
50.
DietterichT.Ensemble methods in machine learning. In: International workshop on multiple classifier systems. New York City: Springer, 2000, pp. 1–15.
51.
AslamJMontagueM.Models for metasearch. In Proceedings of the ACM SIGIR conference on research and development in information retrieval, 2001, pp. 276–284, New York, NY: ACM. DOI: 10.1145/383952.384007.
52.
RendleS.Factorization machines. In: Proceedings of the IEEE international conference on data mining, 2010, pp. 995–1000. New York: IEEE. DOI: 10.1109/ICDM.2010.127.
53.
LouYCaruanaRGehrkeJ, et al. Accurate intelligible models with pairwise interactions. In: Proceedings of the ACM conference on knowledge discovery and data mining, 2013, pp. 623–631. New York: ACM. DOI: 10.1145/2487575.2487579.
54.
DongYChawlaNSwamiA. Metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the ACM SIGKDD conference on knowledge discovery and data mining, 2017, pp. 135–144. New York: ACM. DOI: 10.1145/3097983.3098036.
55.
GoodfellowIBengioYCourvilleA. Deep learning. Cambridge: The MIT Press, 2016.
56.
DredzeMCrammerKPereiraF.Confidence-weighted linear classification. In: Proceedings of the international conference on machine learning, 2008, pp. 264–271. New York: Association for Computing Machinery. DOI: 10.1145/1390156.1390190.
57.
PascanuRMikolovTBengioY. On the difficulty of training recurrent neural networks. In: Proceedings of the international conference on machine learning, 2013, pp. 1310–1318. Atlanta: PMLR.
58.
ChenTTangLSunY, et al. Entity embedding-based anomaly detection for heterogeneous categorical events. In: Proceedings of the international joint conference on artificial intelligence, 2016, pp. 1396–1403. New York: AAAI Press.
59.
RobertsJ.State of the art: coordinated & multiple views in exploratory visualization. In: Proceedings of the international conference on coordinated and multiple views in exploratory visualization, 2007, pp. 61–71. New York: IEEE. DOI: 10.1109/CMV.2007.20.
60.
JavedWElmqvistN. Exploring the design space of composite visualization. In: Proceedings of the IEEE pacific symposium on visualization, 2012, pp. 1–8. New York: IEEE. DOI: 10.1109/PacificVis.2012.6183556.
61.
GleicherM.Considerations for visualizing comparison. IEEE Trans Vis Comput Graph2018; 24(1): 413–423.
LiptonZC.The mythos of model interpretability. Commun ACM2018; 61(10): 36–43.0.
64.
ChooJLiuS.Visual analytics for explainable deep learning. IEEE Comput Graph Appl2018; 38(4): 84–92.
65.
HohmanFKahngMPientaR, et al. Visual analytics in deep learning: an interrogative survey for the next frontiers. IEEE Trans Vis Comput Graph2019; 25(8): 2674–2693.
66.
RibeiroMSinghSGuestrinC. “Why should I trust you?” Explaining the predictions of any classifier. In: Proceedings of the ACM conference on knowledge discovery and data mining, 2016, pp. 1135–1144. New York: ACM. DOI: 10.1145/2939672.2939778.
67.
LundbergSLeeS.A unified approach to interpreting model predictions. In: Proceedings of the international conference on neural information processing systems, 2017, pp. 4768–4777. Red Hook, NY: Curran Associates Inc.
68.
NoriHJenkinsSKochP, et al. InterpretML: a unified framework for machine learning interpretability. arXiv preprint arXiv:1909.09223, 2019.
69.
ShubhomoyDIslamMJayakodiN, et al. Active anomaly detection via ensembles: Insights, algorithms, and interpretability. arXiv preprint arXiv:1901.08930, 2019.
70.
McInnesLHealyJMelvilleJ.Umap: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
71.
TatuAAlbuquerqueGEisemannM, et al. Combining automated analysis and visualization techniques for effective exploration of high-dimensional data. In: Proceedings of the IEEE symposium on visual analytics science and technology, 2009, pp. 59–66. New York: IEEE, 2009. DOI: https://doi.org/10.1109/VAST.2009.5332628.
72.
van der MaatenLHintonG. Visualizing data using t-SNE. J Mach Learn Res2008; 9(86): 2579–2605.
73.
RiehmannPManfredHFroehlichB.Interactive Sankey diagrams. In: Proceedings of the IEEE symposium on information visualization, 2005, pp. 233–240. New York: IEEE. DOI: 10.1109/INFVIS.2005.1532152.
74.
YangJPengWWardM, et al. Interactive hierarchical dimension ordering, spacing and filtering for exploration of high dimensional datasets. In: Proceedings of the IEEE symposium on information visualization, 2003, pp. 105–112. New York: IEEE. DOI: 10.1109/INFVIS.2003.1249015.
75.
SetionoBHuseinY.Fighting forest crime and promoting prudent banking for sustainable forest management: The anti money laundering approach. CIFOR, 2005. DOI: 10.17528/cifor/001881.
76.
HamiltonWYingRLeskovecJ. Inductive representation learning on large graphs. In: Proceedings of the international conference on neural information processing systems, 2017, pp. 1025–1035, Red Hook, NY: Curran Associates Inc. DOI: 10.5555/3294771.3294869.
77.
JohnsonJDouzeMJégouH.Billion-scale similarity search with gpus. In: IEEE Transactions on Big Data, 2019, pp. 1–1. New York: IEEE. DOI: 10.1109/TBDATA.2019.2921572.
