MODULE O5 DEEP LEARNING, MINING, ANALYTICS Deep learning neural networks Convolutional neural networks Long term short term memory Cognitive computing Text mining – Web mining – Social mining Streaming and location analytics Arun Kumar Bhaskara-Baba / Blair Williams – For Class discussion purposes only Give your audience the information they need, in the order they need it, in words designed to be clear, concise, and winsome.* What is the Lysol demand for the next 12 months? The demand for the next 12 months is unknown due to the pandemic being a major disruptor to the industry. Things to consider is the distribution of the vaccine and its timeline, which may increase consumer confidence and decrease demand for Lysol. At the same time, this may not necessarily mean the demand returns to pre-pandemic levels despite decreasing. Another scenario may be that the vaccine is not distributed to majority of the population yet and so demand will remain at pandemic levels. Another possibility is that despite the widespread vaccine distribution, the public continues to consume Lysol at pandemic levels. The future “normal levels” are still unknown but are important for the business to understand how to best adjust the supply chain so that the needed resources are available and being utilized. How can I retain customers that have historically been dependent on gas cars? This is particularly relevant to marketing. I want to find which “groupings” of customers will buy an electric vehicle. But the dynamic part about it is that I can market the car in any way I want. This could mean releasing commercials in only certain parts of the world, sending information to business and advertising expensive cars to only rich customers. This is not exhaustive, of course. https://magazine.wharton.upenn.edu/digital/6-tips-for-clear-and-concise-business-communication/ *USC Marshall Business school https://www.marshall.usc.edu/sites/default/files/2020-01/Communicating-Clearly-Concisely-Persuasively.pdf Give your audience the information they need, in the order they need it, in words designed to be clear, concise, and winsome.* One business question that can be improved using predictive analysis is “How much discount can I give on each product?”. As previously determined, this is a Classification type question so it can be answered using classification techniques such as Decision tree analysis, Rough Sets, and Case-based reasoning predictive analysis is a magic solution to help us solve one of the questions raised before and that play a very effective role The profit of the product depends upon the sales of the product and the cost to manufacture and market the product. A hyperplane concept can be used to separate a profitable product https://magazine.wharton.upenn.edu/digital/6-tips-for-clear-and-concise-business-communication/ *USC Marshall Business school https://www.marshall.usc.edu/sites/default/files/2020-01/Communicating-Clearly-Concisely-Persuasively.pdf Give your audience the information they need, in the order they need it, in words designed to be clear, concise, and winsome.* TEAM PROJECT - STATUS Deep Learning – Mining – Analytics – Learning Objectives ❑ Learn what deep learning is and how it is changing the world of computing ❑ Know the underlying concept and methods for deep neural networks ❑ Understand how convolutional neural networks (C N N), recurrent neural networks (R N N), and long short-memory networks (L S T M) work ❑ Know the foundational details about cognitive Computing and I B M Watson ❑ Describe text mining and understand the need for text mining and differentiate among text analytics, text mining and data mining ❑ Describe sentiment analysis, and Develop familiarity with popular applications of sentiment analysis ❑ Become familiar with speech analytics as it relates to sentiment analysis ❑ Learn three facets of Web analytics—content, structure, and usage mining ❑ Know social analytics including social media and social network analyses ❑ Understand the need for and appreciate the capabilities of stream analytics and learn about the applications of stream analytics ❑ Describe how geospatial and location-based analytics are assisting organizations ANALYTICS, DATA SCIENCE AND AI: SYSTEMS FOR DECISION SUPPORT Eleventh Edition Chapter 6 Deep Learning and Cognitive Computing Chapter 7 Slide in this Presentation Contain Hyperlinks. JAWS users should beSentiment able to get a list of links by using Text Mining, Analysis, and INSERT+F77 Social Analytics Chapter 9 (2 sections) Streaming Analytics and Location Analyticss Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved ACCURACY OF MODELS In classification problems, the primary source for accuracy estimation is the confusion matrix Accuracy = TP + TN TP + TN + FP + FN 𝑇𝑟𝑢𝑒 𝑃𝑜𝑠𝑖𝑡𝑖𝑣𝑒 𝑅𝑎𝑡𝑒(𝑆𝑒𝑛𝑠𝑖𝑡𝑖𝑣𝑖𝑡𝑦) = 𝑇𝑃 𝑇𝑃 + 𝐹𝑁 𝑇𝑟𝑢𝑒 𝑁𝑒𝑔𝑎𝑡𝑖𝑣𝑒 𝑅𝑎𝑡𝑒 𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦 = Precision = TP TP + FP Recall = TP TP + FN 𝑇𝑁 𝑇𝑁 + 𝐹𝑃 ESTIMATION METHODOLOGIES : SINGLE/SIMPLE SPLIT Simple split (or holdout or test sample estimation)  Split the data into 2 mutually exclusive sets: training (~70%) and testing (30%)  For Neural Networks, the data is split into three sub-sets (training [~60%], validation [~20%], testing [~20%]) WHAT IS A MODELER? Instances Instances Instances Instance Modeler New instance Model Classifier Class Class Class Class A mathematical/algorithmic approach to generalize from instances so it can make predictions about instances that it has not seen before Its output is called a model 10 Introduction to Deep Learning • Imaginative things in the SciFi movies are turning into realities-tanks to AI and Machine Learning – Siri, Google assistant, Alexa, Google home, … • Deep learning is the newest member of the AI/Machine Learning family – Learn better than ever before • The reason for Deep Learning superiority – Automatic feature extraction and representation Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Introduction to Deep Learning • Differences between Classic Machine-Learning Methods and Representation Learning/Deep Learning Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Technology Insight 6.1 Elements of an Artificial Neural Network • Processing element (PE) • Network structure – Hidden layer(s) • Input • Output • Connection weights • Summation function • Transfer function Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Basics of “Shallow” Learning • Artificial Neural Networks – abstractions of human brain and its complex biological network of neurons • Neurons = Processing Elements (PEs) • Single-input and single-output neuron/PE Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Basics of “Shallow” Learning • Typical multiple-input neuron with R individual inputs n = w1,1 p1 + w1,2 p2 + w1,3 p3 + ... + w1, R pR + b n = Wp + b Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Technology Insight 6.1 Elements of an Artificial Neural Network • Neural Network with One Hidden Layer Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Technology Insight 6.1 Elements of an Artificial Neural Network Summation Functions Transfer Function Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Process of Developing Neural-Network Based Systems • A process with constant feedbacks for changes and improveme nts! 1. Compute temporary outputs. 2. Compare outputs with desired targets. 3. Adjust the weights and repeat the process. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Backpropagation for ANN Training 1. 2. 3. 4. 5. Initialize weights with random values Read in the input vector and the desired output Compute the actual output via the calculations Compute the error. Change the weights by working backward Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Backpropagation for ANN Training • Illustration of the Overfitting in ANN Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Illuminating the Black Box of ANN • ANN are typically known as black boxes • Sensitivity analysis can shed light to the black-box Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Application Case 6.4 Sensitivity Analysis Reveals Injury Severity Factors in Traffic Accidents • Graphical representation of the sensitivity analysis results for the eight binary ANN model configurations Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Deep Neural Networks • Deep: more hidden layers • In addition to CPU, it also uses GPU – With programming languages like CUDA by NVIDIA • Needs large datasets • Deep learning uses tensors as inputs – Tensor: N-dimensional arrays – Image representation with 3-D tensors • There are different types and capabilities of Deep Neural Networks for different tasks/purposes Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Deep Neural Networks Feedforward Multilayer Perceptron (MLP)-Type Deep Networks • Most common type of deep networks • Vector Representation of the First Three Layers in a Typical MLP Network. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Deep Neural Networks • Impact of Random Weights in Deep MLP • The Effect of Pretraining Network Parameters on Improving Results of a Classification-Type Deep Neural Network. • More hidden layers versus more neurons? Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Application Case 6.5 Georgia DOT Variable Speed Limit Analytics Help Solve Traffic Congestions Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Convolutional “Deep” Neural Networks • Most popular MLP-base DL method • Used for image/video processing, text recognition • Has at least one convolution weight function – Convolutional layer • Convolutional layer → Polling (sub-sampling) – Consolidating the large tensors into one with a smaller size-and reducing the number of model parameters while keeping only the important features – There can be different types of polling layers Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Convolution Function • Typical Convolutional Network Unit • Convolution of a 2 x 2 Kernel by a 3 x 6 Input Matrix Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Image Processing Using CNN • ImageNet (http://www.image-net.org) • Architecture of AlexNet, a CNN for Image Classification Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Image Processing Using CNN • Conceptual Representation of the Inception Feature in GoogLeNet Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Image Processing Using CNN • Examples of Using the Google Lens Figure 6.28 Two Examples of Using the Google Lens, a Service Based on Convolutional Deep Networks for Image Recognition. Source: ©2018 Google LLC, used with permission. Google and the Google logo are registered trademarks of Google LLC. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Consider learning an image: ⚫Some patterns are much smaller than the whole image Can represent a small region with fewer parameters “beak” detector Same pattern appears in different places: They can be compressed! What about training a lot of such “small” detectors and each detector must “move around”. “upper-left beak” detector They can be compressed to the same parameters. “middle beak” detector Why Pooling ⚫ Subsampling pixels will not change the object bird bird Subsampling We can subsample the pixels to make image smaller fewer parameters to characterize the image https://people.cs.pitt.edu/~xianeizhang/notes/NN/NN.html Copyright © 2020 by Pearson Education, Inc. All Rights Reserved Text Processing Using CNN • Google word2vec project – Word embeddings • Typical Vector Representation of Word Embeddings in a Two-Dimensional Space Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Processing Using CNN • CNN Architecture for Relation Extraction Task in Text Mining Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Recurrent Neural Networks (RNN) • RNN designed to process sequential inputs • Typical recurrent unit Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved The referee blew his _________ (whistle) I went to a carwash yesterday. It was raining a lot. It cost $5 to wash _______ (my car) Copyright © 2020 by Pearson Education, Inc. All Rights Reserved Long Short-Term Memory (LSTM) • LSTM is a variant of RNN – In a dynamic network, the weights are called the longterm memory while the feedbacks role is the shortterm memory Typical Long Short-Term Memory (L S T M) Network Architecture Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Recurrent Neural Networks (RNN) & Long Short-Term Memory (LST M) • LSTM Network Applications Example Indicating the Close-toHuman Performance of the Google Neural Machine Translator (G N M T) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Application Case 6.7 Deliver Innovation by Understanding Customer Sentiments Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Computer Frameworks for Implementation of Deep Learning • Torch (http://www.torch.ch) – ML with GPU • Caffe (caffe.berkeleyvision.org) – Facebook’s improved version (www.caffe2.ai) – Pyorch.ai • TensorFlow (www.tensorflow.org) – Google - Tensor Processing Units (TPUs) • Theano (deeplearning.net/software/theano) – Deep Learning Group at the University of Montreal • Keras (keras.io) – Application Programming Interface Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Cognitive Computing • Systems that use mathematical models to emulate (or partially simulate) the human cognition process to find solutions to complex problems and situations where the potential answers can be imprecise • IBM Watson on Jeopardy! • How does cognitive computing work? – – – – Adaptive Interactive Iterative and stateful Contextual • • • • Data mining, Pattern recognition, Deep learning, and N LP – Mimic the way the human brain works Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Cognitive Computing • How does cognitive computing differ from AI? Table 6.3 Cognitive Computing versus Artificial Intelligence (AI). Characteristic Cognitive Computing Artificial Intelligence (AI) Technologies used • Machine learning • Natural language processing • Neural networks • Deep learning • Text mining • Sentiment analysis • Machine learning • Natural language processing • Neural networks • Deep learning Capabilities offered Simulate human thought processes to assist humans in finding solutions to complex problems Find hidden patterns in a variety of data sources to identify problems and provide potential Solutions Purpose Augment human capability Automate complex processes by acting like a human in certain Situations Industries Customer service, marketing, healthcare, entertainment, service Sector Manufacturing, finance, healthcare, banking, securities, retail, government Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Cognitive Search • Can handle a variety of data types • Can contextualize the search space • Employ advanced AI technologies. • Enable developers to build enterprise-specific search applications Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Analytics and Text Mining Figure 7.2 Text Analytics, Related Application Areas, and Enabling Disciplines. • Text Analytics versus Text Mining • Text Analytics = – Information Retrieval + – Information Extraction + – Data Mining + – Web Mining or simply – Text Analytics = Information Retrieval + Text Mining Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Data Mining versus Text Mining • Both seek for novel and useful patterns • Both are semi-automated processes • Difference is the nature of the data: – Structured versus unstructured data – Structured data: in databases – Unstructured data: Word documents, PDF files, text excerpts, XML files, and so on • To perform text mining – first, impose structure to the data, then mine the structured data. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Application Area • Information extraction • Topic tracking • Summarization • Categorization • Clustering • Concept linking • Question answering Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Terminology • Unstructured or semistructured data • Term dictionary • Corpus (and corpora) • Word frequency • Terms • Part-of-speech tagging • Concepts • Morphology • Stemming • Term-by-document matrix – Occurrence matrix • Stop words (and include words) • Synonyms (and polysemes) • Tokenizing • Singular value decomposition – Latent semantic indexing Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Copyright © 2020 by Pearson Education, Inc. All Rights Reserved Natural Language Processing (NLP) • Structuring a collection of text – Old approach: bag-of-words – New approach: natural language processing • NLP is … – a very important concept in text mining – a subfield of artificial intelligence and computational linguistics – the studies of "understanding" the natural human language • Syntax- versus semantics-based text mining Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Natural Language Processing (NLP) • Challenges in NLP – Part-of-speech tagging – Text segmentation – Word sense disambiguation – Syntax ambiguity – Imperfect or irregular input – Speech acts • Dream of AI community – to have algorithms that are capable of automatically reading and obtaining knowledge from text Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved NLP Task Categories • Question answering • Automatic summarization • Natural language generation & understanding • Machine translation • Foreign language reading & writing • Speech recognition • Text proofing, optical character recognition • Optical character recognition Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • A Context Diagram for Text Mining Process Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process Figure 7.6 The Three-Step/Task Text Mining Process. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • Step 1: Establish the corpus – Collect all relevant unstructured data (e.g., textual documents, XML files, emails, Web pages, short notes, voice recordings…) – Digitize, standardize the collection (e.g., all in ASCII text files) – Place the collection in a common place (e.g., in a flat file, or in a directory as separate files) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • Step 2: Create the Term–by–Document Matrix Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • Step 2: Create the Term–by–Document Matrix (TDM) (Cont.) – Should all terms be included? ▪ Stop words, include words ▪ Synonyms, homonyms ▪ Stemming – What is the best representation of the indices (values in cells)? ▪ Row counts; binary frequencies; log frequencies; ▪ Inverse document frequency Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • Step 2: Create the Term–by–Document Matrix (TDM) (Cont.) – TDM is a sparse matrix. How can we reduce the dimensionality of the TDM? ▪ Manual - a domain expert goes through it ▪ Eliminate terms with very few occurrences in very few documents (?) ▪ Transform the matrix using singular value decomposition (SVD) ▪ SVD is similar to principle component analysis Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Text Mining Process • Step 3: Extract patterns/knowledge – Classification (text categorization) – Clustering (natural groupings of text) ▪ Improve search recall ▪ Improve search precision ▪ Scatter/gather ▪ Query-specific clustering – Association – Trend Analysis (…) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Sentiment Analysis • Sentiment → belief, view, opinion, and conviction • Sentiment analysis is trying to answer the question “What do people feel about a certain topic?” • By analyzing data related to opinions of many using a variety of automated tools • Used in variety of domains, but it application in CRM are especially noteworthy (which related to customers/consumers’ opinions) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Sentiment Analysis Applications • Voice of the customer (VOC) • Voice of the Market (VOM) • Voice of the Employee (VOE) • Brand Management • Financial Markets • Politics • Government Intelligence • … others Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Sentiment Analysis Process Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Sentiment Analysis Process • Step 1 – Sentiment Detection – Comes right after the retrieval and preparation of the text documents – It is also called detection of objectivity ▪ Fact [= objectivity] versus Opinion [= subjectivity] • Step 2 – N-P Polarity Classification – Given an opinionated piece of text, the goal is to classify the opinion as falling under one of two opposing sentiment polarities ▪ N [= negative] versus P [= positive] Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Sentiment Analysis Process • Step 3 – Target Identification – The goal of this step is to accurately identify the target of the expressed sentiment (e.g., a person, a product, and event, etc.) ▪ Level of difficulty → the application domain • Step 4 – Collection and Aggregation – Once the sentiments of all text data points in the document are identified and calculated, they are to be aggregated ▪ Word → Statement → Paragraph → Document Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Mining Overview • Web is the largest repository of data • Data is in HTML, XML, text format • Challenges (of processing Web data) – The Web is too big for effective data mining – The Web is too complex – The Web is too dynamic – The Web is not specific to a domain – The Web has everything • Opportunities and challenges are great! Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Mining Web mining (or Web data mining) is the process of discovering intrinsic relationships from Web data (textual, linkage, or usage) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Usage Mining • Extraction of information from data generated through Web page visits and transactions… – data stored in server access logs, referrer logs, agent logs, and client-side cookies – user characteristics and usage profiles – metadata, such as page attributes, content attributes, and usage data • Clickstream data • Clickstream analysis Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Usage Mining • Web usage mining applications – Determine the lifetime value of clients – Design cross-marketing strategies across products. – Evaluate promotional campaigns – Target electronic ads and coupons at user groups based on user access patterns – Predict user behavior based on previously learned rules and users’ profiles – Present dynamic information to users based on their interests and profiles –… Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Search Engines • Google, Bing, Yahoo, … • For what reason do you use search engines? • Search engine is a software program that searches for documents (Internet sites or files) based on the keywords (individual words, multi-word terms, or a complete sentence) that users have provided that have to do with the subject of their inquiry • They are the workhorses of the Internet Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Structure of a Typical Internet Search Engine Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Anatomy of a Search Engine 1. Development Cycle – Web Crawler – Document Indexer 2. Response Cycle – Query Analyzer – Document Matcher/Ranker Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Search Engine Optimization • It is the intentional activity of affecting the visibility of an ecommerce site or a Web site in a search engine’s natural (unpaid or organic) search results • Part of an Internet marketing strategy • Based on knowing how a Search Engine works – Content, HTML, keywords, external links, … • Indexing based on … – Webmaster submission of URL – Proactively and continuously crawling the Web Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Top 15 Most Popular Search Engines (by eBizMBA, August 2016) Rank Name Estimated Unique Monthly Visitors 1 Google 2 Bing 400,000,000 3 Yahoo! Search 300,000,000 4 Ask 245,000,000 5 AOL Search 125,000,000 6 Wow 100,000,000 7 WebCrawler 65,000,000 8 MyWebSearch 60,000,000 9 Infospace 24,000,000 10 Info 13,500,000 11 DuckDuckGo 11,000,000 12 Contenko 10,500,000 13 Dogpile 7,500,000 14 Alhea 4,000,000 15 ixQuick 1,000,000 1,600,000,000 Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Analytics Metrics • Web site usability – How were the visitors using my Web site? • Traffic sources – Where did they come from? • Visitor profiles – What do my visitors look like? • Conversion statistics – What does it all mean for the business? Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Analytics Metrics Web Site Usability Traffic Source • Page views • Referral Web sites • Time on site • Search engines • Downloads • Direct • Click map • Offline campaigns • Click paths • Online campaigns Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Web Analytics Metrics Visitor Profiles Conversion Statistics • Keywords • New visitors • Content groupings • Returning visitors • Geography • Leads • Time of day • Sales/conversions • Landing page profiles • Abandonment/exit rate Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved A Sample Web Analytics Dashboard Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Social Analytics Social Network Analysis • Social Network - social structure composed of individuals link to each other • Analysis of social dynamics • Interdisciplinary field – Social psychology – Sociology – Statistics – Graph theory Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Social Analytics Social Network Analysis • Social Networks help study relationships between individuals, groups, organizations, societies – Self organizing – Emergent – Complex • Typical social network types – Communication networks, community networks, criminal networks, innovation networks, … Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Social Analytics Social Network Analysis Metrics • Connections – Homophily – Multiplexity – Mutuality/reciprocity – Network closure – Propinquity • Distribution – Bridge – Centrality – Density – Distance – Structural holes • Segmentation – Cliques and social circles – Clustering coefficient – Cohesion Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Social Media Analytics • It is the systematic and scientific ways to consume the vast amount of content created by Web-based social media outlets, tools, and techniques for the betterment of an organization’s competitiveness • Tools to measure social media impact: – Descriptive analytics – Social network analysis – Advanced analytics Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Best Practices in Social Media Analytics • Think of measurement as a guidance system, not a rating system • Track the elusive sentiment • Continuously improve the accuracy of text analysis • Look at the ripple effect • Look beyond the brand • Identify your most powerful influencers • Look closely at the accuracy of your analytic tool • Incorporate social media intelligence into planning Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Stream Analytics • Data-in-motion analytics and real-time data analytics – One of the Vs in Big Data = Velocity • Analytic process of extracting actionable information from continuously flowing data • Why Stream Analytics? – It may not be feasible to store the data, or lose its value • Stream Analytics Versus Perpetual Analytics • Critical Event Processing? Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Stream Analytics A Use Case in Energy Industry Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Stream Analytics Applications • e-Commerce • Telecommunication • Law Enforcement and Cyber Security • Power Industry • Financial Services • Health Services • Government https://www.linkedin.com/pulse/fascinating-examplesshow-why-streaming-data-real-time-bernard-marr/ Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved https://docs.microsoft.com/en-us/azure/architecture/solution-ideas/articles/iot-predictive-maintenance Copyright © 2020 by Pearson Education, Inc. All Rights Reserved https://docs.microsoft.com/en-us/azure/architecture/solution-ideas/articles/defect-prevention-with-predictive-maintenance Copyright © 2020 by Pearson Education, Inc. All Rights Reserved https://www.emersonautomationexperts.com/2013/industry/life-sciencesmedical/establishing-a-process-analytical-technology-program/ https://gmpua.com/World/Ma/07/j.htm Copyright © 2020 by Pearson Education, Inc. All Rights Reserved https://ibsen.com/applications/spectroscopy/spectroscopy-for-process-analytical-technology-pat/ Copyright © 2020 by Pearson Education, Inc. All Rights Reserved Location-Based Analytics • Geospatial analytics / GIS • Agricultural, crime, disease spread applications Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved https://blogs.oracle.com/analytics/have-you-everconsidered-location-analytics-to-optimize-your-businessspace Copyright © 2020 by Pearson Education, Inc. All Rights Reserved DEMONSTRATE A COMMITMENT TO SOCIAL DISTANCING While it’s likely there is a widely variable tolerance for risk among the various members of your on-campus community, it makes sense to consider strategies that maximize the number of people willing to return for the fall. Thinking creatively about ways to build on the foundational steps outlined above can help inspire peace of mind for the greatest number of students, their parents, and staff. Strategic Partnership with Degree Analytics Deployed into your existing campus WiFi network by Apogee, the location analytics module from Degree Analytics is a software platform that uses anonymized data and machine learning to log WiFi access by zones you designate. The tool generates visualizations – heat maps – of zone utilization and dwell time and can be used to gauge social distancing compliance on a zone-by-zone basis. https://www.apogee.us/location-analytics/ Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Copyright © 2020 by Pearson Education, Inc. All Rights Reserved Location-Based Analytics • A Multimedia Exercise in Analytics Employing Geospatial Analytics – www.teradatauniversitynetwork.com/Library/Samples/ BSI-The-Case-of-the-Dropped-Mobile-Calls • Real-Time Location Intelligence • Analytics Applications for Consumers – Waze – Yelp – ParkPGH – … Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Leadership Copyright © 2020, 2017, 2014 Pearson Education, Inc. S7 - 98 https://www.entrepreneur.com/article/27483 1 CITATIONS & BACKUP SLIDES Citations • • • • • • • • • • • • • • • • • • • • • • Art of Analytics: Safety Cloud - YouTube Success.com Mareana.com Overview of Mareana COVID-19 app (Enterprise version) on Vimeo https://www.entrepreneur.com/article/274831 https://yecommunity.com/en/blog/fail-fast-fail-often-fail-forward www.teradatauniversitynetwork.com/Library/Samples/BSI-The-Case-of-the-Dropped-Mobile-Calls https://www.apogee.us/location-analytics/ https://blogs.oracle.com/analytics/have-you-ever-considered-location-analytics-to-optimize-your-business-space https://ibsen.com/applications/spectroscopy/spectroscopy-for-process-analytical-technology-pat/ https://docs.microsoft.com/en-us/azure/architecture/solution-ideas/articles/iot-predictive-maintenance https://docs.microsoft.com/en-us/azure/architecture/solution-ideas/articles/defect-prevention-with-predictive-maintenance https://www.emersonautomationexperts.com/2013/industry/life-sciences-medical/establishing-a-process-analytical-technology-program/ https://cs.uwaterloo.ca/~mli/Deep-Learning-2017-Lecture5CNN.ppt https://gmpua.com/World/Ma/07/j.htm What is Text Mining? – YouTube Watson and the Jeopardy! Challenge - YouTube http://www.torch.ch Pyorch.ai TensorFlow (www.tensorflow.org) Theano (deeplearning.net/software/theano) Keras (keras.io) Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved Copyright This work is protected by United States copyright laws and is provided solely for the use of instructors in teaching their courses and assessing student learning. Dissemination or sale of any part of this work (including on the World Wide Web) will destroy the integrity of the work and is not permitted. The work and materials from it should never be made available to students except by instructors using the accompanying text in their classes. All recipients of this work are expected to abide by these restrictions and to honor the intended pedagogical purposes and the needs of other instructors who rely on these materials. Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved CNN/RNN/LSTM-MODELS This century's stark reality is that the business environment has become more dynamic and challenging as organizations are constantly exposed to an array of business problems. One of the most common business problems experienced by organizations and businesses across the globe is the poor management of finances. In particular, changes in financial management remain a severe issue in the PVC Plumbing pipe Industry as various organizations in this industry have continued to grapple with ensuring successful and effective management of their finances, given that some of the available models are not suitable for analyzing certain types of financial data. Over the years, more organizations have turned to CNN/RNN/LSTM models to ensure proper management of finances. these models have the potential to effectively analyze sophisticated and noisy financial data, thus allowing organizations to ensure accuracy. Hence, it will help solve the business problem by allowing individuals to obtain data features from larger numbers of raw data without struggling. There are various decisions that can be made based on the outcome of the data. For instance, the involved parties will make decisions concerning finances and how to ensure increased profitability. The kind of data that will be needed includes both qualitative and quantitative data. Particularly, the data that will be required include the industry's financial data, which consists of sales, expenditures, and profitability. Structured questionnaires will be used to collect the required quantitative and qualitative data. One of the steps that I have to take to make sure the model is relevant is training the organizations within this industry. After that, testing and validation of the model will be carried out to make sure that it is relevant. Text Mining The inability to predict customer perceptions about a particular company or industry and their purchasing behavior is yet another common problem in the present business environment. Particularly, predicting consumer perception and purchasing behavior has continued to challenge the PVC Plumbing pipe industry despite the efforts put in place to develop an improved understanding of their behaviors. Text mining will help solve this particular business problem to enhance cross-selling and up-selling by examining call centers' data. The data will provide the industry with detailed information on customers' perceptions of its products and services. Some of the decisions that can be made based on the outcome of the model include decisions about the kind of products to provide and those that the industry should stop producing. Other decisions that can be made based on the outcome of the model are those concerning how to increase the quality of the industry's products to ensure improved customer experiences. The data that will be needed include demographic data to help understand the industry's products, how they are selling, and who likes them. The data will be collected through structured questionnaires. Some of the steps that will be followed include training the involved parties, testing, and validating the model to make sure that it remains relevant. Web Mining/ Web Analytics Apart from the above-mentioned problems, organizations worldwide, especially the PVC Plumbing pipe industry, are still trying to come to terms with the rate at which technology is accelerating the pace of change. In this respect, the rate at which the pace of change is accelerating due to technology is another serious business problem. Industries are increasingly becoming concerned with how technology is transforming their operations, and they find it to be such a serious problem because they are not certain of what they should do to adapt to this highly changing environment. Web mining or web analytics can be used to address the above business problem by allowing those in this industry to extract relevant and appropriate data from the web. There is no doubt that those in the industry will develop a better understanding of the changes taking place in the present business environment through web mining. The kind of decisions that can be made based on this model's outcome include decisions about how to compete favorably in the present business environment. The kind of data that will be required includes data concerning technological changes taking place and the extent to which they are impacting this industry. The data will be collected through online surveys. The first step that I will have to take to make sure the model is relevant is the training of all the participants. Thereafter, the model will be tested before being validated. Streaming Analytics Another serious business problem in the present corporate world, particularly in the PVC Plumbing pipe Industry, is the inability to accurately predict the demand of its products and services as well as the production in a timely manner. Streaming analytics helps address this business problem by allowing organizations in this industry to apply transaction-level logic to real-time observations. The decisions that can be made based on the outcome of this model are those concerning how the industry can make its offers creative and price offers. The data that will be needed include data concerning the industry's price offers, its products, the products that are constantly looked for by customers, and how often the customers do shop for its products. The steps to be followed include training, testing, and validation of the model to make sure that it is relevant and effective. Location Analytics Exploding data is also considered to be a severe business problem in the present corporate world, specifically in the PVC Plumbing Pipe Industry. Research has shown that over 85% of the world's data was created in the past few years, and managing, ensuring safety, and obtaining important insights from the ever-growing amounts of data is becoming a big problem to organizations in this industry. Location analytics addresses this problem by adding an extra layer of geolocation information to the already existing business data. Some of the decisions that can be made based on the outcome of the model include those about the kind of data to be extracted, transactions, and events. The data that will be needed will be data concerning their customers, their needs and preferences, and data concerning the industry's sales. The data will be collected through online surveys, and steps that will be followed include training, testing, and validation.
Purchase answer to see full attachment