Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics

El sector del gas natural desempeña un papel fundamental a nivel mundial en la actual transición energética, sirviendo como puente clave entre los combustibles fósiles tradicionales y las fuentes de energía renovables. En este trabajo, presentamos una metodología para detectar anomalías en el consum...

Full description

Autores:: Luna Velasco, María Camila
Benavides Sanclemente, María Alejandra

Tipo de recurso:: Trabajo de grado de pregrado

Fecha de publicación:: 2025

Institución:: Universidad de los Andes

Repositorio:: Séneca: repositorio Uniandes

Idioma:: eng

id	UNIANDES2_e646e51842162971bbc47bb166910db5
oai_identifier_str	oai:repositorio.uniandes.edu.co:1992/76232
network_acronym_str	UNIANDES2
network_name_str	Séneca: repositorio Uniandes
repository_id_str
dc.title.eng.fl_str_mv	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
dc.title.alternative.spa.fl_str_mv	Detección de Anomalías en el Consumo de Gas de Clientes Industriales
title	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
spellingShingle	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics Deep Learning Neural Networks Time series analysis Wavelet Transform Anomaly detection Natural gas consumption Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) Aprendizaje profundo Redes neuronales Análisis de series temporales Transformada wavelet Detección de anomalías Consumo de gas natural Redes neuronales convolucionales Memoria a largo y corto plazo Ingeniería
title_short	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
title_full	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
title_fullStr	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
title_full_unstemmed	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
title_sort	Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics
dc.creator.fl_str_mv	Luna Velasco, María Camila Benavides Sanclemente, María Alejandra
dc.contributor.advisor.none.fl_str_mv	Perez Bernal, Juan Fernando Reyes Gomez, Juan Pablo
dc.contributor.author.none.fl_str_mv	Luna Velasco, María Camila Benavides Sanclemente, María Alejandra
dc.contributor.jury.none.fl_str_mv	Rodriguez Castelblanco, Astrid Xiomara
dc.subject.keyword.none.fl_str_mv	Deep Learning Neural Networks Time series analysis Wavelet Transform Anomaly detection Natural gas consumption Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) Aprendizaje profundo Redes neuronales Análisis de series temporales Transformada wavelet Detección de anomalías Consumo de gas natural Redes neuronales convolucionales Memoria a largo y corto plazo
topic	Deep Learning Neural Networks Time series analysis Wavelet Transform Anomaly detection Natural gas consumption Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) Aprendizaje profundo Redes neuronales Análisis de series temporales Transformada wavelet Detección de anomalías Consumo de gas natural Redes neuronales convolucionales Memoria a largo y corto plazo Ingeniería
dc.subject.themes.spa.fl_str_mv	Ingeniería
description	El sector del gas natural desempeña un papel fundamental a nivel mundial en la actual transición energética, sirviendo como puente clave entre los combustibles fósiles tradicionales y las fuentes de energía renovables. En este trabajo, presentamos una metodología para detectar anomalías en el consumo de gas natural industrial, mediante la transformación de datos de series temporales en representaciones de imágenes utilizando la Transformada Wavelet Continua (CWT). Estos escalogramas, que conservan información tanto temporal como de frecuencia, se utilizan como entradas para redes neuronales convolucionales (CNN) y una arquitectura híbrida CNN–Long Short-Term Memory (LSTM), diseñada para capturar patrones espaciales y dependencias secuenciales. Los modelos fueron entrenados y evaluados con datos operativos reales de clientes industriales, alcanzando puntuaciones F1 superiores a 0,80 en la mayoría de los casos. El análisis exploratorio mostró que los comportamientos normales y anómalos generan patrones basados en wavelets visualmente distintos, lo cual apoya tanto la clasificación supervisada como la interpretabilidad por parte de expertos humanos. Entre las arquitecturas probadas, MobileNetV2 y el modelo CNN-LSTM ofrecieron los resultados más estables y generalizables. Este trabajo demuestra que la integración de transformaciones wavelet con aprendizaje profundo mejora significativamente la detección temprana y confiable de anomalías en los sistemas de distribución de gas.
publishDate	2025
dc.date.accessioned.none.fl_str_mv	2025-06-04T20:43:32Z
dc.date.available.none.fl_str_mv	2025-06-04T20:43:32Z
dc.date.issued.none.fl_str_mv	2025-05-21
dc.type.none.fl_str_mv	Trabajo de grado - Pregrado
dc.type.driver.none.fl_str_mv	info:eu-repo/semantics/bachelorThesis
dc.type.version.none.fl_str_mv	info:eu-repo/semantics/acceptedVersion
dc.type.coar.none.fl_str_mv	http://purl.org/coar/resource_type/c_7a1f
dc.type.content.none.fl_str_mv	Text
dc.type.redcol.none.fl_str_mv	http://purl.org/redcol/resource_type/TP
format	http://purl.org/coar/resource_type/c_7a1f
status_str	acceptedVersion
dc.identifier.uri.none.fl_str_mv	https://hdl.handle.net/1992/76232
dc.identifier.instname.none.fl_str_mv	instname:Universidad de los Andes
dc.identifier.reponame.none.fl_str_mv	reponame:Repositorio Institucional Séneca
dc.identifier.repourl.none.fl_str_mv	repourl:https://repositorio.uniandes.edu.co/
url	https://hdl.handle.net/1992/76232
identifier_str_mv	instname:Universidad de los Andes reponame:Repositorio Institucional Séneca repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.none.fl_str_mv	eng
language	eng
dc.relation.references.none.fl_str_mv	Popivanov, I., & Miller, R. J. (2002). Similarity search over time-series data using wavelets. Proceedings of the 18th International Conference on Data Engineering (ICDE), 233–243. https://doi.org/10.1109/ICDE. 2002.994711 Zhao, X. (2022). Wavelet-Attention CNN for Image Classification. arXiv preprint arXiv:2201.09271. https://arxiv.org/abs/2201.09271 Wang, L., & Sun, Y. (2022). Image classification using convolutional neural network with wavelet domain inputs. IET Image Processing, 16(8), 2037–2048. https://doi.org/10.1049/ipr2.12466 Aditi, M. K. N., & Poovammal, E. (2019). Image classification using a hybrid LSTM-CNN deep neural network. International Journal of Engineering and Advanced Technology (IJEAT), 8(6), 1342–1348. https://doi.org/10.35940/ijeat.F8602.088619 Akouemo, H. N., & Povinelli, R. J. (2016). Probabilistic anomaly detection in natural gas time series data. International Journal of Forecasting, 32(3), 948–956. https://doi.org/10.1016/j.ijforecast.2015.06.001 A. Abu Nassar, W.G. Morsi. (2024). Detection of Cyber-Attacks and Power Disturbances in Smart Digital Substations using Continuous Wavelet Transform and Convolution Neural Networks. IEEE Access, 9, 108784–108796. https://doi.org/10.1016/j.epsr.2024.110157 Alhussein, M., Alharbi, A., Aydin, N., & Alshazly, H. (2023). Detection of Cyber Attacks on Smart Grids Using Improved VGG19 Deep Neural Network Architecture and Aquila Optimizer Algorithm. IEEE Access, 11, 88342–88356. http://dx.doi.org/10.21203/rs.3.rs-3217829/v1 Baldacci, L., Golfarelli, M., Lombardi, D., & Sami, F. (2016). Natural gas consumption forecasting for anomaly detection. Expert Systems with Applications, 62, 190–201. https://doi.org/10.1016/j.eswa.2016.06.013 Dash, N., Chakravarty, S., Rath, A. K., & Tripathy, R. (2025). An optimized LSTM-based deep learning model for anomaly network intrusion detection. Scientific Reports, 15, 1554. https://www. researchgate.net/publication/387897520 An optimized LSTM-based deep learning model for anomaly network intrusion detection P. Wu and H. Guo. (2019). LuNet: A Deep Neural Network for Network Intrusion Detection. Applied Soft Computing, 113, 107924. https://ieeexplore.ieee.org/abstract/document/9003126 Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4510–4520. doi: 10.1109/CVPR.2018.00474. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learn- ing for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. doi: 10.1109/CVPR.2016.90. Simonyan, K., & Zisserman, A. (2014). Very Deep Convolu- tional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556. https://arxiv.org/abs/1409.1556 International Energy Agency (IEA) (2024), The Role of Gas in Today’s Energy Transitions, IEA Report, 2019. Available at: https://www.iea.org/ reports/the-role-of-gas-in-todays-energy-transitions Kanarachos, S., Christopoulos, S-R., Chroneos, A., et al., Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform, Expert Systems with Applications. https://doi.org/10.1016/j.eswa.2017.04.028 Industrial Scientific. (2022) Understanding Real-Time Area Gas Monitoring: Importance and Benefits, Connected Safety—Industrial Scientific https://www.indsci.com/en/blog/ understanding-real-time-area-gas-monitoring-importance-benefits Torrence, C., & Compo, G. P. (1998). A practical guide to wavelet analysis. Bulletin of the American Meteorological Society, 79(1), 61–78. https://doi.org/10.1175/1520-0477(1998)079%3C0061: APGTWA%3E2.0.CO;2
dc.rights.en.fl_str_mv	Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri.none.fl_str_mv	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.accessrights.none.fl_str_mv	info:eu-repo/semantics/openAccess
dc.rights.coar.none.fl_str_mv	http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv	Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv	openAccess
dc.format.extent.none.fl_str_mv	17 páginas
dc.format.mimetype.none.fl_str_mv	application/pdf
dc.publisher.none.fl_str_mv	Universidad de los Andes
dc.publisher.program.none.fl_str_mv	Ingeniería de Sistemas y Computación Ingeniería Industrial
dc.publisher.faculty.none.fl_str_mv	Facultad de Ingeniería
dc.publisher.department.none.fl_str_mv	Departamento de Ingeniería de Sistemas y Computación Departamento de Ingeniería Industrial
publisher.none.fl_str_mv	Universidad de los Andes
institution	Universidad de los Andes
bitstream.url.fl_str_mv	https://repositorio.uniandes.edu.co/bitstreams/18b665ab-6777-46fd-b290-b47241734d3d/download https://repositorio.uniandes.edu.co/bitstreams/8fedffdc-a82e-4570-a807-b4fc4cbe2681/download https://repositorio.uniandes.edu.co/bitstreams/312ef211-45cb-402a-976b-4c3cf722758c/download https://repositorio.uniandes.edu.co/bitstreams/1a4cf2cd-2ac0-46d2-9c8c-cf35d47cd267/download https://repositorio.uniandes.edu.co/bitstreams/db33cf7e-d100-44cb-bd12-fbc35c0c691e/download https://repositorio.uniandes.edu.co/bitstreams/67f87e44-3305-41e2-8bc7-69123e0b84a4/download https://repositorio.uniandes.edu.co/bitstreams/10ed51b7-1d9d-4acd-a61e-53a67ecc4bb4/download https://repositorio.uniandes.edu.co/bitstreams/c3b0a096-8d39-4617-a768-e5aa5d2667d8/download
bitstream.checksum.fl_str_mv	042eb8b46955c25c6a8320cf75b02f92 fb23f1eba9fc4b512fd547c39f8fe6d8 4460e5956bc1d1639be9ae6146a50347 ae9e573a68e7f92501b6913cc846c39f ec3db377f77452adc727fe59df7f74ad a5b55759057768b7b73db064c70b4aed 263027a4c741f19c19d88853eaa87514 1b9dd940ba3e969949cdd0ca0668145b
bitstream.checksumAlgorithm.fl_str_mv	MD5 MD5 MD5 MD5 MD5 MD5 MD5 MD5
repository.name.fl_str_mv	Repositorio institucional Séneca
repository.mail.fl_str_mv	adminrepositorio@uniandes.edu.co
_version_	1837005070478082048
spelling	Perez Bernal, Juan FernandoReyes Gomez, Juan PabloLuna Velasco, María CamilaBenavides Sanclemente, María AlejandraRodriguez Castelblanco, Astrid Xiomara2025-06-04T20:43:32Z2025-06-04T20:43:32Z2025-05-21https://hdl.handle.net/1992/76232instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/El sector del gas natural desempeña un papel fundamental a nivel mundial en la actual transición energética, sirviendo como puente clave entre los combustibles fósiles tradicionales y las fuentes de energía renovables. En este trabajo, presentamos una metodología para detectar anomalías en el consumo de gas natural industrial, mediante la transformación de datos de series temporales en representaciones de imágenes utilizando la Transformada Wavelet Continua (CWT). Estos escalogramas, que conservan información tanto temporal como de frecuencia, se utilizan como entradas para redes neuronales convolucionales (CNN) y una arquitectura híbrida CNN–Long Short-Term Memory (LSTM), diseñada para capturar patrones espaciales y dependencias secuenciales. Los modelos fueron entrenados y evaluados con datos operativos reales de clientes industriales, alcanzando puntuaciones F1 superiores a 0,80 en la mayoría de los casos. El análisis exploratorio mostró que los comportamientos normales y anómalos generan patrones basados en wavelets visualmente distintos, lo cual apoya tanto la clasificación supervisada como la interpretabilidad por parte de expertos humanos. Entre las arquitecturas probadas, MobileNetV2 y el modelo CNN-LSTM ofrecieron los resultados más estables y generalizables. Este trabajo demuestra que la integración de transformaciones wavelet con aprendizaje profundo mejora significativamente la detección temprana y confiable de anomalías en los sistemas de distribución de gas.The natural gas industry, plays a critical role worldwide in the current energy transition, serving as a key bridge between traditional fossil fuels and renewable energy sources. We present a methodology for detecting anomalies in industrial natural gas consumption by transforming time series data into image representations using the Continuous Wavelet Transform (CWT). These scalograms, which preserve both temporal and frequency information, are used as inputs to convolutional neural networks (CNN) and a hybrid CNN–Long Short-Term Memory (LSTM) architecture designed to capture both spatial patterns and sequential dependencies. The models were trained and evaluated on real operational data from industrial customers, achieving F1-score above 0.80 in most cases. Exploratory analysis showed that normal and anomalous behaviors produce visually distinct wavelet-based patterns, supporting both supervised classification and human interpretability. Among the architectures tested, MobileNetV2 and the CNN-LSTM model offered the most stable and generalizable results. This work demonstrates that integrating wavelet transformations with deep learning enhances early and reliable anomaly detection in gas distribution systems.Pregrado17 páginasapplication/pdfengUniversidad de los AndesIngeniería de Sistemas y ComputaciónIngeniería IndustrialFacultad de IngenieríaDepartamento de Ingeniería de Sistemas y ComputaciónDepartamento de Ingeniería IndustrialAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Implementation of ananomaly detection system for gas consumption in industrial clients through data analyticsDetección de Anomalías en el Consumo de Gas de Clientes IndustrialesTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPDeep LearningNeural NetworksTime series analysisWavelet TransformAnomaly detectionNatural gas consumptionConvolutional Neural Networks (CNN)Long Short-Term Memory (LSTM)Aprendizaje profundoRedes neuronalesAnálisis de series temporalesTransformada waveletDetección de anomalíasConsumo de gas naturalRedes neuronales convolucionalesMemoria a largo y corto plazoIngenieríaPopivanov, I., & Miller, R. J. (2002). Similarity search over time-series data using wavelets. Proceedings of the 18th International Conference on Data Engineering (ICDE), 233–243. https://doi.org/10.1109/ICDE. 2002.994711Zhao, X. (2022). Wavelet-Attention CNN for Image Classification. arXiv preprint arXiv:2201.09271. https://arxiv.org/abs/2201.09271Wang, L., & Sun, Y. (2022). Image classification using convolutional neural network with wavelet domain inputs. IET Image Processing, 16(8), 2037–2048. https://doi.org/10.1049/ipr2.12466Aditi, M. K. N., & Poovammal, E. (2019). Image classification using a hybrid LSTM-CNN deep neural network. International Journal of Engineering and Advanced Technology (IJEAT), 8(6), 1342–1348. https://doi.org/10.35940/ijeat.F8602.088619Akouemo, H. N., & Povinelli, R. J. (2016). Probabilistic anomaly detection in natural gas time series data. International Journal of Forecasting, 32(3), 948–956. https://doi.org/10.1016/j.ijforecast.2015.06.001A. Abu Nassar, W.G. Morsi. (2024). Detection of Cyber-Attacks and Power Disturbances in Smart Digital Substations using Continuous Wavelet Transform and Convolution Neural Networks. IEEE Access, 9, 108784–108796. https://doi.org/10.1016/j.epsr.2024.110157Alhussein, M., Alharbi, A., Aydin, N., & Alshazly, H. (2023). Detection of Cyber Attacks on Smart Grids Using Improved VGG19 Deep Neural Network Architecture and Aquila Optimizer Algorithm. IEEE Access, 11, 88342–88356. http://dx.doi.org/10.21203/rs.3.rs-3217829/v1Baldacci, L., Golfarelli, M., Lombardi, D., & Sami, F. (2016). Natural gas consumption forecasting for anomaly detection. Expert Systems with Applications, 62, 190–201. https://doi.org/10.1016/j.eswa.2016.06.013Dash, N., Chakravarty, S., Rath, A. K., & Tripathy, R. (2025). An optimized LSTM-based deep learning model for anomaly network intrusion detection. Scientific Reports, 15, 1554. https://www. researchgate.net/publication/387897520 An optimized LSTM-based deep learning model for anomaly network intrusion detectionP. Wu and H. Guo. (2019). LuNet: A Deep Neural Network for Network Intrusion Detection. Applied Soft Computing, 113, 107924. https://ieeexplore.ieee.org/abstract/document/9003126Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4510–4520. doi: 10.1109/CVPR.2018.00474.He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learn- ing for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. doi: 10.1109/CVPR.2016.90.Simonyan, K., & Zisserman, A. (2014). Very Deep Convolu- tional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556. https://arxiv.org/abs/1409.1556International Energy Agency (IEA) (2024), The Role of Gas in Today’s Energy Transitions, IEA Report, 2019. Available at: https://www.iea.org/ reports/the-role-of-gas-in-todays-energy-transitionsKanarachos, S., Christopoulos, S-R., Chroneos, A., et al., Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform, Expert Systems with Applications. https://doi.org/10.1016/j.eswa.2017.04.028Industrial Scientific. (2022) Understanding Real-Time Area Gas Monitoring: Importance and Benefits, Connected Safety—Industrial Scientific https://www.indsci.com/en/blog/ understanding-real-time-area-gas-monitoring-importance-benefitsTorrence, C., & Compo, G. P. (1998). A practical guide to wavelet analysis. Bulletin of the American Meteorological Society, 79(1), 61–78. https://doi.org/10.1175/1520-0477(1998)079%3C0061: APGTWA%3E2.0.CO;2201920993202121944PublicationORIGINALImplementation of an Anomaly Detection System for Gas Consumption.pdfImplementation of an Anomaly Detection System for Gas Consumption.pdfapplication/pdf7544693https://repositorio.uniandes.edu.co/bitstreams/18b665ab-6777-46fd-b290-b47241734d3d/download042eb8b46955c25c6a8320cf75b02f92MD52AutorizacionDocumentosFirmado.pdfAutorizacionDocumentosFirmado.pdfHIDEapplication/pdf339987https://repositorio.uniandes.edu.co/bitstreams/8fedffdc-a82e-4570-a807-b4fc4cbe2681/downloadfb23f1eba9fc4b512fd547c39f8fe6d8MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.uniandes.edu.co/bitstreams/312ef211-45cb-402a-976b-4c3cf722758c/download4460e5956bc1d1639be9ae6146a50347MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/1a4cf2cd-2ac0-46d2-9c8c-cf35d47cd267/downloadae9e573a68e7f92501b6913cc846c39fMD54TEXTImplementation of an Anomaly Detection System for Gas Consumption.pdf.txtImplementation of an Anomaly Detection System for Gas Consumption.pdf.txtExtracted texttext/plain61625https://repositorio.uniandes.edu.co/bitstreams/db33cf7e-d100-44cb-bd12-fbc35c0c691e/downloadec3db377f77452adc727fe59df7f74adMD55AutorizacionDocumentosFirmado.pdf.txtAutorizacionDocumentosFirmado.pdf.txtExtracted texttext/plain1163https://repositorio.uniandes.edu.co/bitstreams/67f87e44-3305-41e2-8bc7-69123e0b84a4/downloada5b55759057768b7b73db064c70b4aedMD57THUMBNAILImplementation of an Anomaly Detection System for Gas Consumption.pdf.jpgImplementation of an Anomaly Detection System for Gas Consumption.pdf.jpgIM Thumbnailimage/jpeg27428https://repositorio.uniandes.edu.co/bitstreams/10ed51b7-1d9d-4acd-a61e-53a67ecc4bb4/download263027a4c741f19c19d88853eaa87514MD56AutorizacionDocumentosFirmado.pdf.jpgAutorizacionDocumentosFirmado.pdf.jpgIM Thumbnailimage/jpeg15283https://repositorio.uniandes.edu.co/bitstreams/c3b0a096-8d39-4617-a768-e5aa5d2667d8/download1b9dd940ba3e969949cdd0ca0668145bMD581992/76232oai:repositorio.uniandes.edu.co:1992/762322025-06-05 04:01:35.028http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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

Implementation of ananomaly detection system for gas consumption in industrial clients through data analytics

Publicaciones similares