Description
Use business intelligence to power corporate growth, increase efficiency, and improve corporate decision making. With this practical book with hands-on examples in Power BI, youll explore the most relevant AI use cases for BI, including improved forecasting, automated classification, and AI-powered recommendations. And youll learn how to draw insights from unstructured data sources like text, document, images files.Author Tobias Zwingmann helps BI professionals, business analysts, and data analytics understand high-impact areas of artificial intelligence. Youll learn how to leverage popular AI-as-a-service and AutoML platforms to ship enterprise-grade proofs of concept without the help of software engineers or data scientists.Learn how AI can generate business impact in BI environmentsUse AutoML for automated classification and improved forecastingImplement recommendation services to support decision-makingDraw insights from text data at scale with NLP servicesExtract information from documents and images with computer vision servicesBuild interactive user frontends for AI-powered dashboard prototypesImplement an end-to-end case study for building an AI-powered customer analytics dashboard Spis treści:PrefaceWho Should Read This BookMicrosoft Power BI and AzureLearning ObjectivesNavigating This BookConventions Used in This BookUsing Code ExamplesOReilly Online LearningHow to Contact UsAcknowledgments1. Creating Business Value with AIHow AI Is Changing the BI LandscapeCommon AI Use Cases for BIAutomation and Ease of UseUsing natural language processing to interact with dataSummarizing analytical resultsUsing automation to find patterns in dataBetter Forecasting and PredictionsLeveraging Unstructured DataGetting an Intuition for AI and Machine LearningMapping AI Use Case Ideas to Business ImpactSummary2. From BI to Decision Intelligence: Assessing Feasibility for AI ProjectsPutting Data FirstAssessing Data Readiness with the 4V FrameworkCombining 4Vs to Assess Data ReadinessChoosing to Make or Buy AI ServicesAI as a ServicePlatform as a ServiceInfrastructure as a ServiceEnd-to-End OwnershipBasic Architectures of AI SystemsUser LayerData LayerAnalysis LayerEthical ConsiderationsCreating a Prioritized Use Case RoadmapMix Champions and Quick WinsIdentify Common Data SourcesBuild a Compelling VisionSummary3. Machine Learning FundamentalsThe Supervised Machine Learning ProcessStep 1: Collect Historical DataStep 2: Identify Features and LabelsStep 3: Split Your Data into Training and Test SetsStep 4: Use Algorithms to Find the Best ModelStep 5: Evaluate the Final ModelStep 6: DeployStep 7: Perform MaintenancePopular Machine Learning AlgorithmsLinear RegressionDecision TreesEnsemble Learning MethodsDeep LearningNatural Language ProcessingComputer VisionReinforcement LearningMachine Learning Model EvaluationEvaluating Regression ModelsEvaluating Classification ModelsEvaluating Multiclassification ModelsCommon Pitfalls of Machine LearningPitfall 1: Using Machine Learning When You Dont Need ItPitfall 2: Being Too GreedyPitfall 3: Building Overly Complex ModelsPitfall 4: Not Stopping When You Have Enough DataPitfall 5: Falling for the Curse of DimensionalityPitfall 6: Ignoring OutliersPitfall 7: Taking Cloud Infrastructure for GrantedSummary4. PrototypingWhat Is a Prototype, and Why Is It Important?Prototyping in Business IntelligenceThe AI Prototyping Toolkit for This BookWorking with Microsoft AzureSign Up for Microsoft AzureCreate an Azure Machine Learning Studio WorkspaceCreate an Azure Compute ResourceCreate Azure Blob StorageWorking with Microsoft Power BISummary5. AI-Powered Descriptive AnalyticsUse Case: Querying Data with Natural LanguageProblem StatementSolution OverviewPower BI Walk-ThroughUse Case: Summarizing Data with Natural LanguageProblem StatementSolution OverviewPower BI Walk-ThroughSummary6. AI-Powered Diagnostic AnalyticsUse Case: Automated InsightsProblem StatementSolution OverviewPower BI Walk-ThroughSummary7. AI-Powered Predictive AnalyticsPrerequisitesAbout the DatasetUse Case: Automating Classification TasksProblem StatementSolution OverviewModel Training with Microsoft Azure Walk-ThroughWhat Is an AutoML Job?Evaluating the AutoML OutputsModel Deployment with Microsoft Azure Walk-ThroughGetting Model Predictions with Python or RModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BIUse Case: Improving KPI PredictionProblem StatementSolution OverviewModel Training with Microsoft Azure Walk-ThroughModel Deployment with Microsoft Azure Walk-ThroughGetting Model Predictions with Python or RModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BIUse Case: Automating Anomaly DetectionProblem StatementSolution OverviewEnabling AI Service on Microsoft Azure Walk-ThroughGetting Model Predictions with Python or RModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BISummary8. AI-Powered Prescriptive AnalyticsUse Case: Next Best Action RecommendationProblem StatementSolution OverviewSetting Up the AI ServiceHow Reinforcement Learning Works with the Personalizer ServiceSetting Up Azure NotebooksSimulating User InteractionsRunning the Simulation with PythonEvaluate Model Performance in Azure PortalModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BISummary9. Leveraging Unstructured Data with AIUse Case: Getting Insights from Text DataProblem StatementSolution OverviewSetting Up the AI ServiceSetting Up the Data PipelineModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BIUse Case: Parsing Documents with AIProblem StatementSolution OverviewSetting Up the AI ServiceSetting Up the Data PipelineModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BIUse Case: Counting Objects in ImagesProblem StatementSolution OverviewSetting Up the AI ServiceSetting Up the Data PipelineModel Inference with Power BI Walk-ThroughBuilding the AI-Powered Dashboard in Power BISummary10. Bringing It All Together: Building an AI-Powered Customer Analytics DashboardProblem StatementSolution OverviewPreparing the DatasetsAllocating a Compute ResourceBuilding the ML WorkflowAdding Sentiment Data to the WorkflowDeploying the Workflow for InferenceBuilding the AI-Powered Dashboard in Power BIAnomaly DetectionPredictive AnalyticsAI-Powered Descriptive AnalyticsUnstructured DataSummary11. Taking the Next Steps: From Prototype to ProductionDiscovery Versus DeliverySuccess Criteria for AI Product DeliveryPeopleProcessesDataTechnologyMLOpsGet Started by Delivering Complete IncrementsConclusionIndex
ile trwa ospa wietrzna, maść z konopii, glosal spray, bebilon 3 profutura, szczoteczki międzyzębowe, migrena u dziecka, lovi smoczek 0-2, maski do inhalatora, jakie probiotyki na trądzik, dvitum forte 2000, co to jest scrub, bio organic henna, smoczki bibs l, plusz dla dzieci, jardiance skutki uboczne, apo amlo, klindamycyna żel
yyyyy
