際際滷shows by User: BohdanPavlyshenko / http://www.slideshare.net/images/logo.gif 際際滷shows by User: BohdanPavlyshenko / Sat, 15 Jan 2022 10:10:00 GMT 際際滷Share feed for 際際滷shows by User: BohdanPavlyshenko Using Consolidated Tabular and Text Data in Business Predictive Analytics /slideshow/using-consolidated-tabular-and-text-data-in-business-predictive-analytics/250999925 pavlyshenkopresentation-220115101001
Speech presentation]]>
Speech presentation]]> Sat, 15 Jan 2022 10:10:00 GMT /slideshow/using-consolidated-tabular-and-text-data-in-business-predictive-analytics/250999925 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) Using Consolidated Tabular and Text Data in Business Predictive Analytics BohdanPavlyshenko Speech presentation <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-220115101001-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Speech presentation
Using Consolidated Tabular and Text Data in Business Predictive Analytics from Bohdan Pavlyshenko
]]> 30 0 https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-220115101001-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Linear, Machine Learning or Probabilistic Predictive Models: What's Best for Time Series Forecasting and Failure Detection? /slideshow/linear-machine-learning-or-probabilistic-predictive-models-whats-best-for-time-series-forecasting-and-failure-detection-144217142/144217142 pavlyshenkopresentation-190507185944
Linear, Machine Learning and Probabilistic models are often used in the predictive analytics. Each of them has its pros and cons for different industrial and business problems. Linear models make it possible to extrapolate forecasting, study impact of external factors but does not allow us to capture nonlinear complicated patterns in the data. Machine learning models can find a complicated pattern but only in the stationary data, at the same time these models require a lot of historical data for training to get sufficient accuracy. Probabilistic models based on the Bayesian inference can take into account expert opinion via prior distributions for parameters and can be used for different kinds of risk assessments. In the speech, I am going to consider the use of these models and their combinations in different use cases. One type of use case is numeric regression for time series forecasting, another one is logistic regression in manufacturing failure detection problems. I will also consider multilevel predictive ensembles of models based on the bagging and stacking approaches.]]>
Linear, Machine Learning and Probabilistic models are often used in the predictive analytics. Each of them has its pros and cons for different industrial and business problems. Linear models make it possible to extrapolate forecasting, study impact of external factors but does not allow us to capture nonlinear complicated patterns in the data. Machine learning models can find a complicated pattern but only in the stationary data, at the same time these models require a lot of historical data for training to get sufficient accuracy. Probabilistic models based on the Bayesian inference can take into account expert opinion via prior distributions for parameters and can be used for different kinds of risk assessments. In the speech, I am going to consider the use of these models and their combinations in different use cases. One type of use case is numeric regression for time series forecasting, another one is logistic regression in manufacturing failure detection problems. I will also consider multilevel predictive ensembles of models based on the bagging and stacking approaches.]]> Tue, 07 May 2019 18:59:44 GMT /slideshow/linear-machine-learning-or-probabilistic-predictive-models-whats-best-for-time-series-forecasting-and-failure-detection-144217142/144217142 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) Linear, Machine Learning or Probabilistic Predictive Models: What's Best for Time Series Forecasting and Failure Detection? BohdanPavlyshenko Linear, Machine Learning and Probabilistic models are often used in the predictive analytics. Each of them has its pros and cons for different industrial and business problems. Linear models make it possible to extrapolate forecasting, study impact of external factors but does not allow us to capture nonlinear complicated patterns in the data. Machine learning models can find a complicated pattern but only in the stationary data, at the same time these models require a lot of historical data for training to get sufficient accuracy. Probabilistic models based on the Bayesian inference can take into account expert opinion via prior distributions for parameters and can be used for different kinds of risk assessments. In the speech, I am going to consider the use of these models and their combinations in different use cases. One type of use case is numeric regression for time series forecasting, another one is logistic regression in manufacturing failure detection problems. I will also consider multilevel predictive ensembles of models based on the bagging and stacking approaches. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-190507185944-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Linear, Machine Learning and Probabilistic models are often used in the predictive analytics. Each of them has its pros and cons for different industrial and business problems. Linear models make it possible to extrapolate forecasting, study impact of external factors but does not allow us to capture nonlinear complicated patterns in the data. Machine learning models can find a complicated pattern but only in the stationary data, at the same time these models require a lot of historical data for training to get sufficient accuracy. Probabilistic models based on the Bayesian inference can take into account expert opinion via prior distributions for parameters and can be used for different kinds of risk assessments. In the speech, I am going to consider the use of these models and their combinations in different use cases. One type of use case is numeric regression for time series forecasting, another one is logistic regression in manufacturing failure detection problems. I will also consider multilevel predictive ensembles of models based on the bagging and stacking approaches.
Linear, Machine Learning or Probabilistic Predictive Models: What's Best for Time Series Forecasting and Failure Detection? from Bohdan Pavlyshenko
]]> 221 2 https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-190507185944-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics /slideshow/linear-machine-learning-and-probabilistic-approaches-for-predictive-analytics/80790926 pavlyshenko-171013203237
Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics ]]>
Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics ]]> Fri, 13 Oct 2017 20:32:37 GMT /slideshow/linear-machine-learning-and-probabilistic-approaches-for-predictive-analytics/80790926 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics BohdanPavlyshenko Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenko-171013203237-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics
Linear, Machine Learning and Probabilistic Approaches for Predictive Analytics from Bohdan Pavlyshenko
]]> 253 3 https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenko-171013203237-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 PresentationMachine Learning, Linear and Bayesian Models for Logistic Regression in Failure Detection Problems /slideshow/presentationmachine-learning-linear-and-bayesian-models-for-logistic-regression-in-failure-detection-problems/69918332 presentation-161207151925
In this work, we study the use of logistic regression in manufacturing failures detection. As a data set for the analysis, we used the data from Kaggle competition Bosch Production Line Performance. We considered the use of machine learning, linear and Bayesian models. For machine learning approach, we analyzed XGBoost tree based classifier to obtain high scored classification. Using the generalized linear model for logistic regression makes it possible to analyze the influence of the factors under study. The Bayesian approach for logistic regression gives the statistical distribution for the parameters of the model. It can be useful in the probabilistic analysis, e.g. risk assessment. ]]>
In this work, we study the use of logistic regression in manufacturing failures detection. As a data set for the analysis, we used the data from Kaggle competition Bosch Production Line Performance. We considered the use of machine learning, linear and Bayesian models. For machine learning approach, we analyzed XGBoost tree based classifier to obtain high scored classification. Using the generalized linear model for logistic regression makes it possible to analyze the influence of the factors under study. The Bayesian approach for logistic regression gives the statistical distribution for the parameters of the model. It can be useful in the probabilistic analysis, e.g. risk assessment. ]]> Wed, 07 Dec 2016 15:19:25 GMT /slideshow/presentationmachine-learning-linear-and-bayesian-models-for-logistic-regression-in-failure-detection-problems/69918332 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) PresentationMachine Learning, Linear and Bayesian Models for Logistic Regression in Failure Detection Problems BohdanPavlyshenko In this work, we study the use of logistic regression in manufacturing failures detection. As a data set for the analysis, we used the data from Kaggle competition Bosch Production Line Performance. We considered the use of machine learning, linear and Bayesian models. For machine learning approach, we analyzed XGBoost tree based classifier to obtain high scored classification. Using the generalized linear model for logistic regression makes it possible to analyze the influence of the factors under study. The Bayesian approach for logistic regression gives the statistical distribution for the parameters of the model. It can be useful in the probabilistic analysis, e.g. risk assessment. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/presentation-161207151925-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> In this work, we study the use of logistic regression in manufacturing failures detection. As a data set for the analysis, we used the data from Kaggle competition Bosch Production Line Performance. We considered the use of machine learning, linear and Bayesian models. For machine learning approach, we analyzed XGBoost tree based classifier to obtain high scored classification. Using the generalized linear model for logistic regression makes it possible to analyze the influence of the factors under study. The Bayesian approach for logistic regression gives the statistical distribution for the parameters of the model. It can be useful in the probabilistic analysis, e.g. risk assessment.
PresentationMachine Learning, Linear and Bayesian Models for Logistic Regression in Failure Detection Problems from Bohdan Pavlyshenko
]]> 259 3 https://cdn.slidesharecdn.com/ss_thumbnails/presentation-161207151925-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Data Mining of Informational Stream 鐃in Social Networks 鐃 /slideshow/data-mining5/27195112 datamining5-131015022346-phpapp02
Data Mining of Informational Stream in Social Networks Forecasting of Social, Market and Financial Trends ]]>
Data Mining of Informational Stream in Social Networks Forecasting of Social, Market and Financial Trends ]]> Tue, 15 Oct 2013 02:23:46 GMT /slideshow/data-mining5/27195112 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) Data Mining of Informational Stream 鐃in Social Networks 鐃 BohdanPavlyshenko Data Mining of Informational Stream 鐃in Social Networks 鐃緒申Forecasting of Social, Market 鐃and Financial Trends <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/datamining5-131015022346-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Data Mining of Informational Stream 鐃in Social Networks 鐃緒申Forecasting of Social, Market 鐃and Financial Trends
Data Mining of Informational Stream in Social Networks from Bohdan Pavlyshenko
]]> 9169 4 https://cdn.slidesharecdn.com/ss_thumbnails/datamining5-131015022346-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. /slideshow/pavlyshenko7/27124366 pavlyshenko7-131012052721-phpapp02
仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. 仂亞仆仂亰于舒仆仆 仂舒仍仆亳, 亠从仂仆仂仄仆亳, 仄舒从亠亳仆亞仂于亳 舒 仆舒仆仂于亳 亠仆亟于 仂舒仍仆亳 仄亠亠亢舒.]]>
仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. 仂亞仆仂亰于舒仆仆 仂舒仍仆亳, 亠从仂仆仂仄仆亳, 仄舒从亠亳仆亞仂于亳 舒 仆舒仆仂于亳 亠仆亟于 仂舒仍仆亳 仄亠亠亢舒.]]> Sat, 12 Oct 2013 05:27:21 GMT /slideshow/pavlyshenko7/27124366 BohdanPavlyshenko@slideshare.net(BohdanPavlyshenko) 仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. BohdanPavlyshenko 仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. 仂亞仆仂亰于舒仆仆 仂舒仍仆亳, 亠从仂仆仂仄仆亳, 仄舒从亠亳仆亞仂于亳 舒 仆舒仆仂于亳 亠仆亟于 仂舒仍仆亳 仄亠亠亢舒. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenko7-131012052721-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. 仂亞仆仂亰于舒仆仆 仂舒仍仆亳, 亠从仂仆仂仄仆亳, 仄舒从亠亳仆亞仂于亳 舒 仆舒仆仂于亳 亠仆亟于 仂舒仍仆亳 仄亠亠亢舒.
仆亠仍亠从舒仍仆亳亶 舒仆舒仍亰 仍舒弍仂从仂于舒仆亳 亟舒仆亳. from Bohdan Pavlyshenko
]]> 460 2 https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenko7-131012052721-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-BohdanPavlyshenko-48x48.jpg?cb=1642241333 Master level at Kaggle (https://www.kaggle.com/bpavlyshenko) My current scientific areas are: Data Mining, Predictive Analytics, Machine Learning, Information Retrieval, Text Mining, Natural Language Processing, R Analytics, Social Network Analysis, Big Data; semantic field approach in the analysis of semi-structured data; semantic approach in machine learning algorithms of classification and clusterization of text documents; analysis of social network informational streams; the use of the theories of formal concept analysis and frequent sets in the data mining of semi-structured data, particularly text streams; the use of numerical characteristics of frequent sets and association rules... http://bpavlyshenko.blogspot.com https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-220115101001-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/using-consolidated-tabular-and-text-data-in-business-predictive-analytics/250999925 Using Consolidated Tab... https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenkopresentation-190507185944-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/linear-machine-learning-or-probabilistic-predictive-models-whats-best-for-time-series-forecasting-and-failure-detection-144217142/144217142 Linear, Machine Learni... https://cdn.slidesharecdn.com/ss_thumbnails/pavlyshenko-171013203237-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/linear-machine-learning-and-probabilistic-approaches-for-predictive-analytics/80790926 Linear, Machine Learni...