<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[author results for Salon, Data,]]></title><description><![CDATA[author results for Salon, Data,]]></description><link>https://gateway.bibliocommons.com/v2/libraries/mpl/rss/search?query=Salon%2C%20Data%2C&amp;searchType=author&amp;origin=core-catalog-explore&amp;view=grouped</link><generator>RSS for Node</generator><lastBuildDate>Wed, 11 Mar 2026 22:21:07 GMT</lastBuildDate><item><title><![CDATA[IoT and Analytics Condition Based Maintenance]]></title><description><![CDATA[Presented by Stanislaw Schmal Combining IoT and sensor analytics opens a new world of operations and maintenance efficiency. A real-world demonstrator of audio analytics and customized IoT device will be shown and its business application to condition based maintenance will be discussed in this session.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620686</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620686</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620686075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[All Models Are Wrong, but Some Are Useful. Especially With the Right Data]]></title><description><![CDATA[Presented by Alex Schwarm - VP/Head of Data Science at Dun & Bradstreet For many teams, the most challenging step in delivering useful results, is less about the modeling techniques and methods and more about having access to the right data with the appropriate data coverage of the domain of interest. In this talk, we will describe two specific use cases where data pays a crucial role: one around identifying supply chain risks and one related to prospect targeting. For the supply chain risk use case, we will describe how access to unique data assets reveals the impact of the Coronavirus on supply chains and how this impacts global businesses. We will also describe how some companies are offering data scientists the ability to access data to determine which data assets best solve their business analytics and modeling needs, with a particular focus on prospect targeting.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620673</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620673</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620673075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Case Studies in Data Driven Merchandising]]></title><description><![CDATA[For retail businesses, inventory is simultaneously the company's greatest asset and its largest risk. Competitor pricing, markdowns, and returns all threaten the margins that drive success, and in practice, inventory doesn't always move according to plan. To win in this highly competitive and rapidly evolving industry, it's essential to have a flexible toolkit that accurately produces forecasts and intelligently adapts to unplanned inventory dynamics. In this talk, I'll outline how Nordstrom applies data science and machine learning to build a wholistic view of inventory management from assortment, through stocking with intelligent size runs, and ending with a customer experience that gets the right product to the right customer at the right time.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620683</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620683</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620683075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Leveraging Entity Resolution to Identify Customers in 3rd Party Data]]></title><description><![CDATA[Presented by Kelsey Redman - AVP, Data Science at Comerica Bank Purchasing 3rd party data on individuals can give great insights on customers, but first we have to know which individuals from that outside data source are actually customers and which are just prospects. Without a unique identifier like SSN or Driver's License number from the 3rd party data, we have to use a combination of name, address, and demographic information to identify the matching customer. Between nicknames, misspelled names and addresses, and family members with similar names all at one address, this quickly becomes a difficult task involving heavy data cleanup and an increasingly complicated series of rules. In this presentation, we demonstrate some techniques to help resolve these entities across data sources by employing the use of supervised classification machine learning techniques to quantify and predict entity "likeness." We showcase some of the challenges we faced with exploring other entity resolution methods, with manually labeling a comprehensive training set, and how this approach might extend to solve other data issues.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620679</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620679</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620679075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Hands on Inquiry Into Algorithmic Bias and Machine Learning Interpretability]]></title><description><![CDATA[Presented by Fatih Akici - Manager, Risk Analytics and Data Science at Populus Financial Group As intelligent systems deepen their footprints in our daily lives, algorithmic bias becomes a more prominent problem in today's world. The position of executives and data science leaders to this issue is generally reactive, in that, companies solely respond to the requirements coming from regulatory agencies. In this presentation, I am going to argue why the leaders should be proactive in identifying biases and how they will benefit from fixing them. I will demonstrate my point on an applied example.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620488</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620488</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620488075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Minority Report]]></title><description><![CDATA[Presented by Michael Zelenetz - Analytics Project Leader at New York-Presbyterian Hospital Forecasting is widely used in a number of business, but can it be used to optimize operations in an emergency department? This talk will walk through the development of a forecasting model to predict future arrivals to the emergency department. We will review the fundamentals of forecasting, discuss feature engineering, and how to get your first forecast off the ground.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620667</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620667</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620667075</comments><format>WEBSITE</format><subtitle>Can We Predict Emergencies</subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Behaviors in Bookkeeping]]></title><description><![CDATA[Bookkeeping is an established process businesses need to follow in order to keep track of their financials and tax returns. When translating a machine learning model into what a customer considers to be 'kept books' and what a bookkeeper considers to be 'kept books' variability and a dependency on the customer-bookkeeper relationship come into play. Some of this can be handled by education and process changes, but other elements can be instilled by creating a logic that is applied before, during and after a machine learning model to control for the various types of error. The presentation will go over the ways we can apply logical algorithms outside of the central model to improve the central model, and create a less error-prone training set and output.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C8607785</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C8607785</guid><category><![CDATA[VIDEO_ONLINE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/8607785075</comments><format>VIDEO_ONLINE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Dark Data & AI Pipelines to Drive Ad Sales & Grow Audiences]]></title><description><![CDATA[Presented by Paul Barrett - Managing Director, Accenture Applied Intelligence Personalization drives more relevant conversations with advertisers and audiences. The key to personalization is data, algorithms and offers. Algorithms feed off data. The data environment is becoming more competitive and more regulated. AI at scale makes it possible to utilize internal and external data sources that were previously too complicated, too expensive or too big. The Dark Data sources can now be utilized to: " Enhance sales leads to drive better propensity scoring, better targeting and drive better sales interactions " Create a deeper understanding of audiences to create more relevant microsegments for better targeting, messaging and greater engagement. Companies that can master AI at scale can create Real-time Analytical Pipelines turning data science into Ai Enhanced customer interactions. Growing sales, Engagement and other key metrics. This talk will cover how companies are leveraging Dark Data and Ai pipelines to transform analytics into Ai enhanced interactions]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C8607774</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C8607774</guid><category><![CDATA[VIDEO_ONLINE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Fri, 31 Jan 2020 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/8607774075</comments><format>VIDEO_ONLINE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Using Deep Learning to Build A Unified E-commerce Marketplace]]></title><description><![CDATA[Presented by Ali Vanderveld, Director of Data Science at ShopRunner ShopRunner is an e-commerce company that receives feeds of product data from over 100 different retailer partners, including large department stores and retailers that specialize in electronics, appliances, nutritional products, and more. In order to provide a great user experience on our website and in our mobile app, we need to have one easy-to-navigate product taxonomy. We also would like to have sets of attribute tags that make it easy to filter down to exactly what any shopper is looking for. In this talk I will describe how we are using computer vision and natural language processing to place all of the products from our retailer partners into one easy-to-navigate shopping experience.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620685</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620685</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620685075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Improving the Worlds Largest Online Grocery Catalog]]></title><description><![CDATA[Presented by Ishant Nayer, Sr Data Scientist at Instacart Being a data-driven company, Instacart realizes the power of good quality data. While trying to maximize the efficiency of data consumption by all work streams such as recommendation systems and availability systems, we are trying to make our Catalog the best in the world by delivering precise information to all our end-users including shoppers and consumers. This session will cover the following areas: 1. How we used data science to auto-detect inconsistencies in the data attributes of millions of items comprising the Catalog, in real-time. 2. How we defined and utilized North Star metrics to optimize data quality of our Catalog 3. Different approaches being used to deliver a great customer experience.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620692</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620692</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620692075</comments><format>WEBSITE</format><subtitle>A Data Science Story</subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Product(ive) Data Science]]></title><description><![CDATA[Presented by Julie Hollek, Sr Data Scientist at Twitter Data scientists are the people behind the scenes, helping others deliver better, smarter results in their daily work. This is especially true for product data scientists who must hone their craft to determine what things are working for a given product, where do we want to take it next, and how can we make product decisions aligned with company is trying to build? Cross-functional communications are critical to success in this role; you need to be able to craft a message that is born out of math to make compelling arguments that are digestible by stakeholders across the business. In this session, we'll define Product Data Science and discuss contributing factors to success.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620691</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620691</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620691075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Rocky Journey to AI Adoption]]></title><description><![CDATA[Presented by Sangeeta Krishnan - Former Director, Enterprise Data Management & Strategy at Asembia Artificial Intelligence (AI) is the current buzz word across all industries. Marvin Minsky's definition of AI describes it as the science of making machines do things that would normally require human intelligence. However, the opinions are split across two camps. On one side we hear about new AI gadgets getting introduced in the market that would empower and improve our lives. At the same time, there are stories of AI companies going bankrupt like the recent closure of AI powered clock - Bonjour. Any digital technology has its own risks such as Cyber Security, Data Privacy Protection, apart from protecting the interests and careers of the human workforce. When you attempt to transform data into answers, many questions erupt. AI is a combination of techniques that includes Data Analytics and Predictive Analytics. Many organizations start their Analytics and AI journey without implementing the discovery phase of defining clear achievable business values. This results in most of the R&D budget to evaporate in experimental pitfalls with no real gain, resulting in AI being non-productive. It is imperative for any organization to discuss and focus on certain fundamental areas and challenges before embarking on the AI journey. This presentation would give a detailed overview of the areas that need to be addressed for the AI journey to be successful beyond PoC (Proof of Concept). It would demystify AI from an implementation stand point and would cover multiple aspects to demonstrate the current capabilities of AI technologies. It would also put out a road map for the industries to have a smooth journey to the AI world. The presentation would discuss the entire spread of activities such as budgeting, risk mitigation, training and many more.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620689</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620689</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620689075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Challenges in Machine Learning From Model Building to Deployment at Scale]]></title><description><![CDATA[Presented by Anupama Joshi Companies are moving towards AI/Machine learning very fast. Data scientist are building models and training models. But challenges come when deploying models in production. How to maintain multiple models? Creating a common platform that allows model management and deployment easily and reliably is becoming a necessity for organizations to accelerate product development. In this talk, I will talk about the challenges faced and the solutions used to make this process easy.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620688</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620688</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620688075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[10 Questions Before You Set up your Data Science Team]]></title><description><![CDATA[Congratulations, you are the new leader of data science at a traditional company. Your customers are internal business units, and everyone is intrigued about the possibilities that data science can bring to the company. You are aware of multiple opportunities to apply a data driven approach and you are ready to jump in. But, wait! Before you start; here are 10 key questions that you may want to ask yourself before you embark on the first project. Knowing how to code or to model will only take you so far, as a leader you are going to have manage several other challenges. The earlier you can answer these questions the faster you will be able to run a successful program.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620674</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620674</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620674075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[On the Road to More Holistic Player Understanding]]></title><description><![CDATA[One of the challenges seemingly all data scientists face is finding a clean data set which contains the state of the player right before they take some event in the system. Typically we need to interact with event-driven systems and/or databases that only maintain the current snapshot of the player. In this talk we highlight some work we have done to recreate the up to date snapshot of the player captured before each event and demonstrate how we can leverage this dataset to improve personalization and model the players' likelihood to churn.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620675</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620675</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620675075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Just Ask]]></title><description><![CDATA[Presented by Anna Schneider, Data Science Manager at Stitch Fix Classic recommender systems are great for answering the question "what does a user want in general?". However, they only get you partway to an answer to "what does a user want right now?". To close the gap, it helps to capture and act on real-time user intent. I'll share two examples of this paradigm, and the resulting changes to our algorithms and architectures at Stitch Fix.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620676</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620676</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620676075</comments><format>WEBSITE</format><subtitle>Designing Intent Driven Algos</subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Interpretable Predictive Models in the Healthcare Domain]]></title><description><![CDATA[Presented by Sridharan Kamalakannan, Head of Data Science at Humana Predictive models are often used to identify individuals that will likely have escalating health severity in the future and accordingly deliver appropriate interventions. However, for the clinicians and care managers, these predictive models often act as a black-box at an individual level. The reason for this being, typically predictive models use combinations of complicated algorithms that makes it hard to explain the reason behind a predictive model score at an individual level. This talk will focus on model and feature agnostic methodologies and techniques that help uncover the drivers behind a prediction at a personal level in a healthcare setting.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620687</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620687</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620687075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[A Product Development Approach to Improving Data Quality]]></title><description><![CDATA[Presented by Dalela Bharati - Product Owner, Data & Analytics at Booking.com Poor data quality (DQ) is crippling to any data scientist. Especially organisation wide complex DQ challenges for fundamental datasets that can take months to fix. This talk/ session outlines the product development approach we adopted to solving a DQ challenge at Booking.com.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620680</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620680</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620680075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Search Engine in Startups]]></title><description><![CDATA[Presented by Liang Wu, Machine Learning Data Scientist at Airbnb Choosing the correct optimization metric is key to success of a search engine. Unlike in traditional web searches, where clicks are clearly the main objective to optimize, many emerging vertical search engines like E-Commerce search may require a different optimization metric, such as conversions, revenue, and quality. Selection of a good metric may depend on the query type (transactional vs. navigational vs. informational) and also on the goal of a business (profitability vs. growth). For example, a typical product search engine may focus on maximizing the number of transactions and total revenue, while navigational search may aim at minimizing the total number of clicks. In this talk, we will investigate factors needed to be considered when we are in search for a good metric, and we will also walk through an example of designing an optimization metric for a particular business, including how it is selected, mathematically defined, and optimized with a machine learning framework.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620681</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620681</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620681075</comments><format>WEBSITE</format><subtitle>What to Optimize</subtitle><language>eng</language><image_url/></item><item><title><![CDATA[How I Learned to Stop Worrying and Love Graph Databases]]></title><description><![CDATA[Presented by Michael Zelenetz - Analytics Project Leader at New York-Presbyterian Hospital Healthcare data is highly connected but often lives in silos. Graph databases are promising emerging technologies for working with highly connected data. This talk will introduce data scientists to Neo4j-the leading graph database-and will discuss a proof of concept implementation at New York Presbyterian and will demonstrate some of the network analyses we were able to do as a result. This talk will be developer/data scientist focused and will include code snippets. We will introduce the graph data model and loading data into the database. We will discuss the pros and cons of graph databases. We will finish off with some practical examples from out proof of concept including community detection algorithms, using centrality to find providers who may be spreading infections, and examining physician referral patterns. Participants will leave being able to describe a graph database. They should be able to identify situations that may benefit from implementing a graph database. Finally, they should be able to create a simple graph model.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620682</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620682</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620682075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Personalization at Scale With AI]]></title><description><![CDATA[Presented by Ayan Bhattacharya - Advanced Analytics Specialist Leader, Deloitte Consulting Conversational AI is the application of a combination of AI and cognitive services including Natural Language Processing, Speech Recognition and Intent Classification. It is focused on bringing voice, chat, and personal assistant technologies to intelligently automate human and technology interactions and improve client's business outcomes as well as engagement with customers. There are varying levels of complexity in the virtual agents or chatbots; some are designed for answering common questions while others have a more complex architecture which includes the ability to disambiguate complex dialog and integrate with machine learning algorithms. The current marketplace for Conversational AI is being driven by cloud enabled platforms such as AWS, GCP, Azure and Watson; and there are over 2000 companies that have started developing their own niche industry solutions.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620684</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620684</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620684075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Literate Statistical Programming Is Not Just About Reproducibility]]></title><description><![CDATA[Presented by John Peach, Sr Data Scientist at Amazon Alexa Science is facing a crisis around reproducibility and data science is not immune. Literate Statistical Programming is a workflow that binds the code used in an analysis to the interpretation of the results. While this creates reproducibility it also addresses issues around, auditing, re-usability and allows for rapid iteration and experimentation. This talk will describe a workflow that I have successfully used on small-scale data-sets in start-ups and on Amazon-scale problems in my work on Alexa. The talk will cover the tooling, workflow, and the philosophy you need to master Literate Statistical Programming.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620664</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620664</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620664075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Using Machine Learning to Target Households in Large Scale Direct Marketing]]></title><description><![CDATA[Finding the right audience is the core marketing puzzle of all e-commerce businesses. While in the past this was mostly achieved using coarse segmentation and personas the broad availability of data makes nowadays possible to learn individual consumer preferences by training large scale machine learning models which can combine knowledge from thousands of dimensions and measurements. HelloFresh is the largest meal kit delivery service worldwide; in this talk, we will review how we use machine learning (gradient boosting machines) to acquire millions of customers every year and describe our large scale model training and scoring infrastructure.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620678</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620678</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620678075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Data and AI for Emerging Platforms]]></title><description><![CDATA[Presented by Kabir Seth - VP Machine Learning & AI Strategy, Wall Street Journal & Alex Siegman - AI Technical Program Manager, Dow Jones Walking through the steps necessary to appropriately leverage AI in a large organization, including tips and tricks for identifying business opportunities that lend themselves to AI, as well as best practices for each step of the AI project management process, all while navigating complex organizational structures.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620670</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620670</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620670075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item><item><title><![CDATA[Algorithmic Recommendations at The New York Times]]></title><description><![CDATA[Presented by Anna Coenen Algorithmic curating at the Times brings many unique challenges. We want our recommendations to feel personal and relevant, but not creepy. We want articles to be timely, yet also showcase older pieces that our readers still enjoy. We want to increase engagement, but without sacrificing editorial judgment. This talk describes how we achieved these goals through a combination of Machine Learning, experimentation, and diligent editorial curation.]]></description><link>https://mpl.bibliocommons.com/v2/record/S75C9620671</link><guid isPermaLink="true">https://mpl.bibliocommons.com/v2/record/S75C9620671</guid><category><![CDATA[WEBSITE]]></category><category><![CDATA[eng]]></category><dc:creator><![CDATA[Salon, Data]]></dc:creator><pubDate>Thu, 31 Jan 2019 00:00:00 GMT</pubDate><comments>https://mpl.bibliocommons.com/item/comment/9620671075</comments><format>WEBSITE</format><subtitle></subtitle><language>eng</language><image_url/></item></channel></rss>