Product Matching: an untapped strategy to fast-track e-commerce
María Paz Cuturi – Machine Learning Engineer at Tryolabs
Product Matching is the process of identifying identical items inside one or more product catalogs. The capability of recognizing if one product is the same as another brings exciting possibilities for the retail industry. In this talk, we will focus on how Product Matching can be applied to e-commerce. Using Product Matching as an internal support system can help automate manual work, translating into millions of cost reductions for big retailers. On the other hand, using it as a competitive advantage can help retailers increase sales and revenue. Product Matching might seem a simple problem at first sight, but it actually is a complex challenge that can be solved with the help of Machine Learning techniques. Join us for more insights on how to fast-track an e-commerce strategy.
María Paz Cuturi
Machine Learning Engineer at Tryolabs
Maria Paz Cuturi is a Machine Learning Engineer with a BSc in Computer Science. She has experience working with distributed Engineering teams applying Agile methodologies. After 2 years as a Developer, her focus has shifted towards Machine Learning and Data Science. Maria Paz also has a background in Marketing through a Bachelor’s Degree in Communications and relevant work experience in the area.
An Experiment-based Framework for Real-time Assignment Optimization
Sifeng Lin – Research Scientist at DoorDash
Common methodologies used to optimize conventional logistics systems are less applicable to improving the efficiency of DoorDash’s real-time last-mile logistics platform. These common methodologies require a stable prototype environment that is difficult to build in our platform and does not allow for the accurate measurement of the algorithm change. To address our specific use case, we designed an experiment-based framework that allows us to rapidly iterate our algorithms and accurately measures the impact of every algorithm change.
Operations Research Scientist at DoorDash
Sifeng Lin works as an operations research scientist in DoorDash. In this role, he combines operations research and software engineering to solve the real-time dispatching problem. He held a Ph.D. in Operations Research from the University of Texas at Austin and previously worked as a Sr. operations research specialist in BNSF Railway.
Why Apache Pulsar is becoming the new cornerstone of event driven retail
Chris Latimer – VP Product Management at DataStax
Retailers face unique challenges when it comes to conducting business and delivering the technology to support it. From coping with Black Friday/Cyber Monday to constant pressures to deliver up to the second data in real time that will inform operational and business decisions, the retail industry is constantly pushing the envelope when it comes to event driven architecture and real time event streaming. In this session, we will take a closer look at Apache Pulsar, the next generation event streaming and messaging platform, to see why this technology is so well equipped to support the needs of today’s retail companies. Whether you need to magnify your visibility into customer activities and behavior, drive efficiencies in your supply chain, or deliver smarter experiences through machine learning and AI, this talk will show you why Apache Pulsar must absolutely be on your company’s radar.
VP Product Management at DataStax
Applying holistic ML to solve Industry business problems
Sayan Maity – Senior Research Data Scientist at Roku
How cutting edge Machine Learning techniques can be leveraged to solve the core business needs of expanding the customer base without impacting the brand perception and by minimizing fraud in the context of product based consumer model.
Senior Research Data Scientist at Roku
Sayan Maity, Ph.D. , is currently leading the effort of researching and applying Cutting Edge AI/ ML techniques in the Ad-Tech business at Roku. Previously, Sayan has worked at Visa Inc. & Walmart Labs in solving business problems in the Fin-Tech & Marketing-Tech domain, respectively. Before joining Industry, Sayan has performed extensive research in academia in developing ML techniques to solve Biometrics, Medical imaging problems and improve optimization techniques in a variety of concave/ convex search spaces.
Industrial POI Analysis: The Future of Data Science in Ecommerce and Retail
Briana Brown – Geographer at Safe Graph
2020 was a watershed year for retail and ecommerce. Some brands and stores experienced sharp declines in revenue due to the economic downturn and social distancing; others saw demand for their products skyrocket, putting stress on supply chain operations as they struggled to keep up with rising consumer expectations. While the economy is now on the road to recovery, some of the shifts in consumer demand, behavior, and expectations will remain, creating a new normal for retail. To adjust to these changes, brands are increasingly turning to data science for answers. Geospatial information like points of interest (POIs), building footprints, and mobility data give retailers and ecommerce brands the tools to analyze how consumers interact with physical store locations, as well as places that may serve as leading indicators of demand to come. But one category of data in particular has been a gamechanger for brands as they adapt to a post-pandemic economy: industrial POIs. Industrial POIs refer to distribution centers, warehouses, and manufacturing facilities that are critical for supply chain analysis and demand forecasting, especially in a retail landscape increasingly dominated by ecommerce. Join geographer Briana Brown from SafeGraph as she describes the different types of industrial POIs and how they can be used for essential retail and ecommerce analytics.
Geographer at Safe Graph
Briana is a geographer specializing in data content, storytelling, and visualization. Currently working in content at SafeGraph, she has previous experience in product management, marketing, and consulting, having previously worked at Precisely and Esri.Briana has also volunteered her GIS and data expertise with the United Nations and Catholic Relief Services. Briana holds a master’s degree in Geographic Information Systems from Penn State University and a bachelor’s degree in Geography from Villanova University. She frequently uses location intelligence platforms such as Esri, Tableau, and QGIS in her geographic storytelling.
Physics, Personalization, and Pizza
Resham Sarkar – Principal Data Scientist at Slice
What if we all had a personal assistant who kept track of our likes and dislikes, when do we like what we like, where is the best place to get what we like? As we continue to ingest astronomical amounts of daily data, personalization has become a necessity for e-commerce companies for retaining high-quality customers and building trust in your brand. But first, we must understand our data. In this talk, I will show how we use physics to decode pizza at Slice and power personalization.
Principal Data Scientist at Slice
Resham Sarkar is a Principal Data Scientist at Slice, where she leads Machine Learning and Personalization. Prior to this, she led the machine learning team at CCC Intelligent Solutions in Chicago, developing state-of-art models for optical character recognition, vehicle damage detection, and injury prediction. She has a Ph.D. in Atomic Physics from Northwestern University. Her research was geared towards building an ultra-sensitive gyroscope that measures slow movements like the rate of expansion of the universe. She is also an actor and a comedian who has been performing since she was three and still feels the same rush every time the lights go up.
Effective use of AI with Limited Data
Edward Ratner – Founder & CEO at Edammo
Though in recent years the focus has been on big data, AI can provide critical in sights even when the amount of data is quite limited. In this talk, we will discuss a new approach to AI pioneered by Edammo. The technology provides very accurate models even when the number of training sample is between 100 and 10,000. We will discuss concrete use cases in several verticals including: image analysis, HR Tech, AI on IOT device and marketing/lead generation. This approach will enable many companies to leverage AI that currently can not. The new technology allows models to be created in seconds on standard desktop computers eliminating the need for expensive GPU clusters and other costly hardware.
Founder & CEO at Edammo
Ed Ratner is the co-founder and CEO of Edammo Inc founded in 2016. Edammo has developed breakthrough AI technology focused on increased prediction accuracy on limited data sets. They were chosen as one of Top 10 AI solution providers by PharmaTech Outlook Magazine. Previously, Ed founded and served as the CTO of Lyrical Labs which was selected for theCableLabs Innovation Showcase in 2012 for its innovative video encoding technology. In 2007, Ed co-founded Keystream Corporation, which was recognized with a 2009 Best of Business Award by Small Business Commerce Association. He was the President of Research & Development and led the creation of Keystreams novel in-video ad insertion product. Additionally, he was the VP of R&D/Chief Scientist at Pulsent Corp., which pioneered a proprietary object-based video codec. Ed also held senior technical positions at KLA-Tencor, Synopsys and Deutsch Research. His work has resulted in 37 issued US patents to date with a number of patents pending and he has co-authored over 20 academic publications. Ed was elevated to Senior Member of IEEE in 2004 and serves as a reviewer for IEEE Transactions on Circuits and Systems for Video Technology and Neurocomputing. Ed is also an accomplished entrepreneur who founded and was a key early employee at several start-ups. He has raised over $10M in investment over the course of his career from a variety of sources including venture capitalists, hedge funds, and professional angel investors. He has built several engineering teams that took the products from conception to market. He has served as the primary point of contact for customers, including negotiating the contracts for all engagements at Edammo, Lyrical Labs and Keystream. Ed received his Ph.D. from Stanford University where he was a Hertz Foundation Fellow. He also won the National Science Foundation and the National Defense Science/Engineering Fellowships. He received his B.S. in Physics from Caltech where he received the Froehlich Prize for most creative junior and was a high scorer on the Putnam Exam Competition scoring among top ten juniors in North America. In 2009, Ed was selected as one of Caltech’s Notable Alumni by Forbes magazine. In 2018, his paper received the Best Paper Award at ELM 2018 international research conference in Singapore.
Metric Learning for Recommendations
Murium Iqbal – Senior Data Scientist at Etsy
Two tower approaches have become prevalent in industry for both Search and Recommendations over the last few years. These methods employ metric learning to enforce a structure on an embedding space which captures a specific type of similarity. Fast retrieval via approximate nearest neighbor look-ups is then available in real time. We will review the loss functions and sampling strategies employed in industry to enable these methods, how they are deployed and why they are so powerful for information retrieval.
Senior Data Scientist at Etsy
Murium is a Senior Data Scientist working on Recommendations at Etsy. She has worked as a data scientist for 7 years working on a mix of recommendations, search and marketing applications at various e-commerce companies. She is located in Salt Lake City, Utah and enjoys outdoor activities and horror movies.
Visual Document Understanding
Dia Trambitas – Head of Product at John Snow Labs
Many businesses depend on paper documents or documents stored as images, such as receipts, manifests, invoices, medical reports, contracts, waivers, leases, forms, and audit records digitized with scanners. Up until now, extracting data from these images mainly involved extracting the text through OCR and using NLP techniques, while neglecting the layout and style information which are often vital for document image understanding. Novel deep learning techniques combine features from computer vision and NLP into unified models, resulting in improved state-of-the-art accuracy for form understanding and visual information extraction. This talk shares real applications of these models to digitize and analyze documents with the purpose of extracting meaningful and easily exploitable data.
Head of Product at John Snow Labs
Dia Trambitas is a computer scientist with a rich background in Natural Language Processing. She has a Ph.D. in Semantic Web from the University of Grenoble, France, where she worked on ways of describing spatial and temporal data using OWL ontologies and reasoning based on semantic annotations. She then changed her interest to text processing and data extraction from unstructured documents, a subject she has been working on for the last 10 years. She has a rich experience working with different annotation tools and leading document classification and NER extraction projects in verticals such as Finance, Investment, Banking, and Healthcare.
Representation Learning Driven Outfit Creation: Assisting Styling to Scale
Brian Burns – Manager of Data Science & Analytics – Personalization & Outfitting at Nordstrom
Nordstrom Digital Stylists create outfits to help our customers look good and feel great. They are asked to create outfits for several reasons: to serve an individual customer, to contribute to a thematic curation, to showcase an individual product, and more! During peak events with lots of new inventory such as the holidays and large sales, demand for their expertise can be enormous. In service of helping our stylists, we have created a machine learning based outfit creation/completion service leveraging Nordstrom’s extensive dataset of expertly created outfits and a hybrid graph based and representation learning approach. Given an initial item or set of items, we create outfits out of available inventory that are difficult to decern from those created by stylists, even by our stylists themselves. Join this talk to hear more about Nordstrom’s approach and results from their recent Anniversary Sale.
Manager of Data Science & Analytics - Personalization & Outfitting at Nordstrom
Brian currently manages a team of stellar data scientists and analysts focused on personalization and outfitting at Nordstrom. Their work entails recommendation systems, AI outfitting, and enhanced personalization in styling. He is delighted to share some of this recent work at this conference. Prior to Nordstrom, Brian’s focus was applying machine learning methods in the wind energy industry, creating patented innovations in turbine failure prediction and turbine performance optimization. Additionally, Brian has experience with the optimization of logistical networks. Residing in the Chicago area, Brian enjoys walks to the park with his son and brewing craft beer.