<p><a href="https://www.linkedin.com/in/chetankumartrivedi/">Chetan Trivedi</a>, Head of Technical Program Management (Verizon Solutions Team), Verizon Media<br/></p><p>I recently spoke at the <a href="https://aiacceleratorsummit.com/">AI Accelerator Summit</a> in San Jose. During my presentation, I shared a few of Verizon Media’s AI Solutions via four machine learning use cases, including:<br/></p><ul><li>Cellular Network Performance Prediction</li><ul><li>Our team implemented a time series prediction model for the performance of base station parameters such as bearer drop, SIP, and handover failure.<br/></li></ul><li>Threat Detection System<br/></li><ul><li>DDoS (Distributed Denial of Service) use case where we implemented a real-time threat detection capability using time series data.<br/></li></ul><li>Automobile Traffic Flow Monitoring<br/></li><ul><li>A collaboration with a city to identify traffic patterns at certain traffic junctions and streets to provide insights so they can improve traffic patterns and also address safety concerns.<br/></li></ul><li>IoT Analytics<br/></li><ul><li>Detecting vending machine anomalies and addressing them before dispatching the service vehicle with personnel to fix the problem which is very costly for the businesses.</li></ul></ul><figure class="tmblr-embed tmblr-full" data-provider="youtube" data-orig-width="540" data-orig-height="304" data-url="https%3A%2F%2Fyoutu.be%2FrLgOO45SEso"><iframe width="540" height="304" id="youtube_iframe" src="https://www.youtube.com/embed/rLgOO45SEso?feature=oembed&amp;enablejsapi=1&amp;origin=https://safe.txmblr.com&amp;wmode=opaque" frameborder="0" allowfullscreen="allowfullscreen"></iframe></figure><p>During the conference, I heard many talks that reinforced common machine learning and AI industry themes. These included:<br/></p><ul><li>Key factors to consider when selecting the right use cases for your AI/ML efforts include understanding your error tolerance and ensuring you have sufficient training data. </li><li>Implementing AI/ML at scale (with a high volume of data) and moving towards deep learning for supported use cases, where data is highly dimensional and/or higher prediction accuracy is required with enough data to train deep learning models.<br/></li><li>Using ensemble learning techniques such as bagging, boosting or other variants of these methods.<br/></li></ul><p>At Verizon Media, we’ve built and open sourced several helpful tools that are focused on big data, machine learning, and AI, including:<br/></p><p><b></b></p><ul><li><a href="https://datasketches.github.io/">DataSketches</a> - high-performance library of stochastic streaming algorithms commonly called &ldquo;sketches&rdquo; in the data sciences.</li><li><a href="https://github.com/yahoo/TensorFlowOnSpark">TensorFlowOnSpark</a> - brings TensorFlow programs to Apache Spark clusters.<br/></li><li><a href="https://github.com/Verizon/trapezium">Trapezium</a> - framework to build batch, streaming and API services to deploy machine learning models using Spark and Akka compute.<br/></li><li><a href="https://vespa.ai">Vespa</a> - big data serving engine.<br/></li></ul><p><b></b></p><p>If you’d like to discuss any of the above use cases or open source projects, feel free to <a href="mailto:%20chetankumar.trivedi@verizonmedia.com">email me</a>.</p>