{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:24:43Z","timestamp":1780583083663,"version":"3.54.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T00:00:00Z","timestamp":1706659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T00:00:00Z","timestamp":1706659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001779","name":"Monash University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001779","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Stat"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The increased predictive power of machine learning models comes at the cost of increased complexity and loss of interpretability, particularly in comparison to parametric statistical models. This trade-off has led to the emergence of eXplainable AI (XAI) which provides methods, such as local explanations (LEs) and local variable attributions (LVAs), to shed light on how a model use predictors to arrive at a prediction. These provide a point estimate of the linear variable importance in the vicinity of a single observation. However, LVAs tend not to effectively handle association between predictors. To understand how the interaction between predictors affects the variable importance estimate, we can convert LVAs into linear projections and use the radial tour. This is also useful for learning how a model has made a mistake, or the effect of outliers, or the clustering of observations. The approach is illustrated with examples from categorical (penguin species, chocolate types) and quantitative (soccer\/football salaries, house prices) response models. The methods are implemented in the R package cheem, available on CRAN.<\/jats:p>","DOI":"10.1007\/s00180-023-01453-2","type":"journal-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T04:46:33Z","timestamp":1706676393000},"page":"1071-1095","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Exploring local explanations of nonlinear models using animated linear projections"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8417-0212","authenticated-orcid":false,"given":"Nicholas","family":"Spyrison","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dianne","family":"Cook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Przemyslaw","family":"Biecek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,31]]},"reference":[{"key":"1453_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:52138\u201352160","journal-title":"IEEE Access"},{"key":"1453_CR2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3905.001.0001","volume-title":"An introduction to neural networks","author":"JA Anderson","year":"1995","unstructured":"Anderson JA (1995) An introduction to neural networks. MIT press, Cambridge"},{"issue":"1","key":"1453_CR3","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1137\/0906011","volume":"6","author":"D Asimov","year":"1985","unstructured":"Asimov D (1985) The grand tour: a tool for viewing multidimensional data. SIAM J Sci Stat Comput 6(1):128\u2013143. https:\/\/doi.org\/10.1137\/0906011","journal-title":"SIAM J Sci Stat Comput"},{"key":"1453_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"A Barredo Arrieta","year":"2020","unstructured":"Barredo Arrieta A, Diaz-Rodriguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garcia S, Gil-Lopez S, Molina D, Benjamins R, Chatila R, Herrera F (2020) Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 58:82\u2013115. https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012","journal-title":"Inf Fusion"},{"issue":"1","key":"1453_CR5","first-page":"3245","volume":"19","author":"P Biecek","year":"2018","unstructured":"Biecek P (2018) DALEX: explainers for complex predictive models in R. J Mach Learn Res 19(1):3245\u20133249","journal-title":"J Mach Learn Res"},{"key":"1453_CR6","doi-asserted-by":"crossref","unstructured":"Biecek P (2020) ceterisParibus: Ceteris Paribus Profiles","DOI":"10.1201\/9780429027192-12"},{"key":"1453_CR7","doi-asserted-by":"publisher","DOI":"10.1201\/9780429027192","volume-title":"Explanatory model analysis: explore, explain, and examine predictive models","author":"P Biecek","year":"2021","unstructured":"Biecek P, Burzykowski T (2021) Explanatory model analysis: explore, explain, and examine predictive models. CRC Press, New York"},{"key":"1453_CR8","doi-asserted-by":"crossref","unstructured":"Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory, pp. 144\u2013152","DOI":"10.1145\/130385.130401"},{"issue":"1","key":"1453_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"issue":"3","key":"1453_CR10","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1214\/ss\/1009213726","volume":"16","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat Sci 16(3):199\u2013231","journal-title":"Stat Sci"},{"key":"1453_CR11","unstructured":"Buja A, Asimov D (1986) Grand tour methods: an outline. In: Proceedings of the seventeenth symposium on the interface of computer sciences and statistics on computer science and statistics, New York, NY, USA, pp. 63\u201367. Elsevier North-Holland, Inc"},{"key":"1453_CR12","first-page":"136","volume-title":"Visual methods for examining SVM classifiers","author":"D Caragea","year":"2008","unstructured":"Caragea D, Cook D, Wickham H, Honavar V (2008) Visual methods for examining SVM classifiers. Springer, Berlin, pp 136\u2013153"},{"key":"1453_CR13","unstructured":"Chang W, Cheng J, Allaire J, Sievert C, Schloerke B, Xie Y, Allen J, McPherson J, Dipert A, Borges B (2021) shiny: web application framework for R"},{"key":"1453_CR14","unstructured":"Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, Chen K, Mitchell R, Cano I, Zhou T, Li M, Xie J, Lin M, Geng Y, Li, Y (2021) xgboost: extreme gradient boosting"},{"issue":"4","key":"1453_CR15","doi-asserted-by":"publisher","first-page":"464","DOI":"10.2307\/1390747","volume":"6","author":"D Cook","year":"1997","unstructured":"Cook D, Buja A (1997) Manual controls for high-dimensional data projections. J Comput Graph Stat 6(4):464\u2013480. https:\/\/doi.org\/10.2307\/1390747","journal-title":"J Comput Graph Stat"},{"key":"1453_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-33037-0_13","volume-title":"Grand tours, projection pursuit guided tours, and manual controls, handbook of data visualization, 295\u2013314","author":"D Cook","year":"2008","unstructured":"Cook D, Buja A, Lee EK, Wickham H (2008) Grand tours, projection pursuit guided tours, and manual controls, handbook of data visualization, 295\u2013314. Springer, Berlin. https:\/\/doi.org\/10.1007\/978-3-540-33037-0_13"},{"key":"1453_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-71762-3","volume-title":"Interactive and Dynamic Graphics for Data Analysis: with R and GGobi","author":"D Cook","year":"2007","unstructured":"Cook D, Swayne DF, Buja A (2007) Interactive and Dynamic Graphics for Data Analysis: with R and GGobi. Springer, Berlin"},{"key":"1453_CR18","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1080\/10618600.2020.1870480","volume":"30","author":"N da Silva","year":"2021","unstructured":"da Silva N, Cook D, Lee EK (2021) A projection pursuit forest algorithm for supervised classification. J Comput Gr Stat 30:1168","journal-title":"J Comput Gr Stat"},{"key":"1453_CR19","doi-asserted-by":"publisher","DOI":"10.1080\/10691898.2011.11889627","author":"D De Cock","year":"2011","unstructured":"De Cock D (2011) Ames Iowa: alternative to the Boston housing data as an end of semester regression project. Journal of Statistics Education. https:\/\/doi.org\/10.1080\/10691898.2011.11889627","journal-title":"Journal of Statistics Education"},{"issue":"3","key":"1453_CR20","doi-asserted-by":"publisher","first-page":"e90081","DOI":"10.1371\/journal.pone.0090081","volume":"9","author":"KB Gorman","year":"2014","unstructured":"Gorman KB, Williams TD, Fraser WR (2014) Ecological sexual dimorphism and environmental variability within a community of Antarctic penguins (genus Pygoscelis). PLoS ONE 9(3):e90081","journal-title":"PLoS ONE"},{"key":"1453_CR21","unstructured":"Gosiewska A, Biecek, P (2019) IBreakDown: uncertainty of model explanations for non-additive predictive models. arXiv preprint arXiv:1903.11420"},{"key":"1453_CR22","doi-asserted-by":"crossref","unstructured":"Greenwell B (2020) fastshap: fast approximate Shapley values","DOI":"10.32614\/CRAN.package.fastshap"},{"key":"1453_CR23","unstructured":"Greenwell B (2023) fastshap: fast approximate Shapley values. R package version 0.1.0"},{"key":"1453_CR24","unstructured":"Greenwell B, Boehmke B, Cunningham J, Developers GBM (2020) gbm: generalized boosted regression models"},{"key":"1453_CR25","doi-asserted-by":"crossref","unstructured":"Horst AM, Hill AP, Gorman KB (2020) palmerpenguins: Palmer Archipelago (Antarctica) penguin data","DOI":"10.32614\/CRAN.package.palmerpenguins"},{"key":"1453_CR26","volume-title":"International encyclopedia of ergonomics and human factors","author":"W Karwowski","year":"2006","unstructured":"Karwowski W (2006) International encyclopedia of ergonomics and human factors, vol 3. CRC Press, Boca Raton"},{"key":"1453_CR27","unstructured":"Kominsarczyk K, Kozminski P, Maksymiuk S, Biecek P (2023) treeshap"},{"key":"1453_CR28","first-page":"5","volume":"2","author":"EK Lee","year":"2022","unstructured":"Lee EK, Cho H (2022) PPtreeregViz: projection pursuit regression tree visualization. R package version 2:5","journal-title":"R package version"},{"key":"1453_CR29","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1573","author":"S Lee","year":"2021","unstructured":"Lee S, Cook D, da Silva N, Laa U, Spyrison N, Wang E, Zhang HS (2021) The state-of-the-art on tours for dynamic visualization of high-dimensional data. WIREs Comput Stat. https:\/\/doi.org\/10.1002\/wics.1573","journal-title":"WIREs Comput Stat"},{"key":"1453_CR30","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1214\/13-EJS810","volume":"7","author":"Y Lee","year":"2013","unstructured":"Lee Y, Cook D, Park JW, Lee EK (2013) PPtree: projection pursuit classification tree. Electron J Stat 7:1369\u20131386","journal-title":"Electron J Stat"},{"key":"1453_CR31","unstructured":"Leone S (2020) FIFA 20 complete player dataset"},{"issue":"3","key":"1453_CR32","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M (2002) Classification and regression by randomForest. R news 2(3):18\u201322","journal-title":"R news"},{"key":"1453_CR33","unstructured":"Lundberg SM, Erion GG, Lee, SI (2018) Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888"},{"key":"1453_CR34","unstructured":"Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, pp. 4768\u20134777"},{"key":"1453_CR35","unstructured":"Mayer M (2023a) flashlight: shed light on black box machine learning models. R package version 0.9.0"},{"key":"1453_CR36","doi-asserted-by":"crossref","unstructured":"Mayer M (2023b) shapviz: SHAP visualizations. R package version 0.9.2","DOI":"10.32614\/CRAN.package.shapviz"},{"key":"1453_CR37","doi-asserted-by":"crossref","unstructured":"Mayer M, Watson D (2023) kernelshap: Kernel SHAP. R package version 0.3.8","DOI":"10.32614\/CRAN.package.kernelshap"},{"key":"1453_CR38","unstructured":"Molnar C (2022) Interpretable Machine Learning (2 ed.)"},{"key":"1453_CR39","unstructured":"Ocagne Md (1885) Coordonn\u00e9es parall\u00e8les et axiales. M\u00e9thode de transformation g\u00e9om\u00e9trique et proc\u00e9d\u00e9 nouveau de calcul graphique d\u00e9duits de la consid\u00e9ration des coordonn\u00e9es parall\u00e9les, par Maurice d\u2019Ocagne, ... Paris: Gauthier-Villars"},{"key":"1453_CR40","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) August. \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201916, New York, NY, USA, pp. 1135\u20131144. Association for Computing Machinery","DOI":"10.1145\/2939672.2939778"},{"key":"1453_CR41","doi-asserted-by":"crossref","unstructured":"Roberts JC (2007) State of the art: coordinated & multiple views in exploratory visualization. In: Fifth international conference on coordinated and multiple views in exploratory visualization (CMV 2007), pp. 61\u201371. IEEE","DOI":"10.1109\/CMV.2007.20"},{"key":"1453_CR42","unstructured":"Robnik-Sikonja M (2018) ExplainPrediction: explanation of predictions for classification and regression models. R package version 1.3.0"},{"key":"1453_CR43","unstructured":"Sellereite N, Jullum M, Redelmeier A (2023) shapr: prediction explanation with dependence-aware shapley values. R package version 0.2.2"},{"key":"1453_CR44","volume-title":"A value for n-person games","author":"LS Shapley","year":"1953","unstructured":"Shapley LS (1953) A value for n-person games. Princeton University Press, princeton"},{"key":"1453_CR45","unstructured":"Shi Y, Ke G, Soukhavong D, Lamb J, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY, Titov N (2022) lightgbm: light gradient boosting machine"},{"issue":"3","key":"1453_CR46","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1214\/10-STS330","volume":"25","author":"G Shmueli","year":"2010","unstructured":"Shmueli G (2010) To explain or to predict? Stat Sci 25(3):289\u2013310","journal-title":"Stat Sci"},{"key":"1453_CR47","unstructured":"Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145\u20133153. PMLR"},{"key":"1453_CR48","unstructured":"Shrikumar A, Greenside P, Shcherbina A, Kundaje A (2016) Not just a black box: learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713"},{"key":"1453_CR49","doi-asserted-by":"publisher","DOI":"10.1201\/9780429447273","volume-title":"Interactive web-based data visualization with R, plotly, and shiny","author":"C Sievert","year":"2020","unstructured":"Sievert C (2020) Interactive web-based data visualization with R, plotly, and shiny. Chapman and Hall\/CRC, Boca Raton"},{"key":"1453_CR50","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2014) Deep inside convolutional networks: visualising image classification models and saliency maps. In In Workshop at International Conference on Learning Representations. Citeseer"},{"key":"1453_CR51","doi-asserted-by":"crossref","unstructured":"Spyrison N (2023) November. cheem: Interactively Explore Local Explanations with the Radial Tour","DOI":"10.32614\/CRAN.package.cheem"},{"issue":"1","key":"1453_CR52","doi-asserted-by":"publisher","first-page":"243","DOI":"10.32614\/RJ-2020-027","volume":"12","author":"N Spyrison","year":"2020","unstructured":"Spyrison N, Cook D (2020) spinifex: an R package for creating a manual tour of low-dimensional projections of multivariate data. R J 12(1):243. https:\/\/doi.org\/10.32614\/RJ-2020-027","journal-title":"R J"},{"key":"1453_CR53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69978-9_4","author":"BC Stahl","year":"2021","unstructured":"Stahl BC (2021) Ethical issues of AI. Artif Intell Better Future. https:\/\/doi.org\/10.1007\/978-3-030-69978-9_4","journal-title":"Artif Intell Better Future"},{"key":"1453_CR54","first-page":"1","volume":"11","author":"E Strumbelj","year":"2010","unstructured":"Strumbelj E, Kononenko I (2010) An efficient explanation of individual classifications using game theory. J Mach Learn Res 11:1\u201318","journal-title":"J Mach Learn Res"},{"issue":"1","key":"1453_CR55","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1080\/10618600.2017.1383264","volume":"27","author":"A Unwin","year":"2018","unstructured":"Unwin A, Valero-Mora P (2018) Ensemble graphics. J Comput Gr Stat 27(1):157\u2013165. https:\/\/doi.org\/10.1080\/10618600.2017.1383264","journal-title":"J Comput Gr Stat"},{"key":"1453_CR56","doi-asserted-by":"crossref","unstructured":"Vanni L, Ducoffe M, Aguilar C, Precioso F, Mayaffre D (2018) Textual deconvolution saliency (TDS): a deep tool box for linguistic analysis. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 548\u2013557","DOI":"10.18653\/v1\/P18-1051"},{"key":"1453_CR57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24277-4","volume-title":"ggplot2: elegant graphics for data analysis","author":"H Wickham","year":"2016","unstructured":"Wickham H (2016) ggplot2: elegant graphics for data analysis. Springer-Verlag, New York"},{"issue":"4","key":"1453_CR58","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1002\/sam.11271","volume":"8","author":"H Wickham","year":"2015","unstructured":"Wickham H, Cook D, Hofmann H (2015) Visualizing statistical models: removing the blindfold. Stat Anal Data Mining ASA Data Sci J 8(4):203\u2013225. https:\/\/doi.org\/10.1002\/sam.11271","journal-title":"Stat Anal Data Mining ASA Data Sci J"},{"issue":"1","key":"1453_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v077.i01","volume":"77","author":"MN Wright","year":"2017","unstructured":"Wright MN, Ziegler A (2017) ranger: a fast implementation of random forests for high dimensional data in C++ and R. J Stat Softw 77(1):1\u201317. https:\/\/doi.org\/10.18637\/jss.v077.i01","journal-title":"J Stat Softw"}],"container-title":["Computational Statistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-023-01453-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00180-023-01453-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-023-01453-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T21:54:56Z","timestamp":1739829296000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00180-023-01453-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,31]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1453"],"URL":"https:\/\/doi.org\/10.1007\/s00180-023-01453-2","relation":{},"ISSN":["0943-4062","1613-9658"],"issn-type":[{"value":"0943-4062","type":"print"},{"value":"1613-9658","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,31]]},"assertion":[{"value":"18 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}