Sri Ambati

machine learning h2o data science h2o.ai big data ai deep learning artificial intelligence h2o world predictive analytics data r open source sparkling water python apache spark spark h2o.ai university distributed applications h2ony hadoop h2oopen analytics meetup driverless ai scalable h2o open dallas h2odallas gbm machine learning big data ensembles gpu glm algorithms arno candel java ensemble learning predictive modeling healthcare insurance kaggle h2o driverless ai erin ledell stanford software alex tellez flow michal malohlava machine learning applications 0xdata data.table caffè capital one machine learning interpretability data engineering modeling nlp smarter applications data munging tensorflow yarn scala classification enterprise h2o gpte math mnist mark landry overfitting automated machine learning cloud paypal goh2o h2onyc databricks data scientists mxnet cliff click glrm generalized low rank models natural language processing chicago sensor data internet of things text mining shiny algorithm random forest comcast data products h2oensemble enterprise baseball medicine san francisco sri ambati llms deep water london progressive gradient boosted models technology pysparkling financial services ai journey ai foundations prediction progressive insurance genai iot kalman filters public safety user clustering cancer craigslist business sas foundations of ai introduction to ai h2o.ai training churn gradient boosting xgboost text analysis ai training text analytics pydata model deployment genomics automatic machine learning generative ai steam visual intelligence cybersecurity ebay automl auto-encoder higgs boson h2oworld interpretability fast azure lime rest fraud detection marketshare regression github stephen boyd consensus lasso business transformation 6sense data analysis aws mlconf data prep workshop generalized linear models optimization strataconf atlanta munging madeleine udell h20 boston reza zadeh generalized linear modeling ad click data product mountain view portland r users corinne horn portland r user group supervised learning principal components analysis pca unsupervised learning pojo developers web applications lending club tokyo ec2 usc ucsb tom kraljevic mich nyc new york bordeaux cycling fight crime wine apache statistics strata open-source distributed glm hadopp jacksonville in-memory super bowl neural networks games neural network k-means cisco predictive model factory advertising adtech outlier detection stanford medicine model kv store distributed fork join h2o infrastructure h2o design h2o architecture user aalborg qconsf userr aalborg parallelism aalborg radix sorting matt dowle performance word gui h2oflow ipython wendy kan citibike dallas bootstrap stefan wagner bootstrap regularization open data city data prithvi prabhu map reduce peter evans thecge r2d3 transformation rstudio sparklyr missing values silicon valley time series microsoft aml security word2vec anti-money laundering code tutorial introduction sparking water hdinsight speed accuracy denver grid search hyperparameter amazon aws lambda design patterns recommendation engine recommendation risk marketing business problems fintech fraud logistic regression vertical datascience hca allison baker venkatesh yadav h2o open ny data alliances digital brain model predictions ml predictions cdf cloudera data flow hedge fund use case workflow ml h2o-3 mrm wells fargo gen ai hydrogen torch h2o ai cloud - caids large language models h2o wave h2o wave starter course learning path enterprise gpte intro to enterprise h2o gpte ai agents nvidia mlb logistic ordinal regression fashion e-learning ibm aginity moneyball lightgbm rulefit intel intel ai feature engineering apache nifi cloudera flow management cfm mojo mojo scoring pipeline server computing custom nifi processor nifi processor development macys riverwood michael marks paxion venture capital customer churn genomes data fellas nbcuniversal cable nbc viewership universal engineering xavier amatriain quora questions save lives kaiser permanente health kaiser predictions h2o ensemble 2015 neural nets adobe integral ads digital advertising pipelines data pipelines data modeling business users zurich zurich north america keen io business decisions linear modeling pysparkling water pitfalls macys.com retail advanced analytics kaiser health data natives monica rogati nielsen catalina catalina nielsen nielsen catalina solutions ontology ontology management trendkite retirement transamerica santa clara university scu la los angeles sensors seattle galvanize data scientist parisoma michal kp risk analysis slang machine zone gaming game of war benchmarks lexalytics k means kmeans api rest api migrating caltech domino reproducible research reproducible domino data lab rob tibshirani lasso cancer detection h2o label genie