Instacart marries retail shopping and ecommerce in a unique way. During the time of a global pandemic more consumers have used online alternatives to the standard grocery shopping. Stores are offering online order placement and pick up. Delivery services are at an all time high. I was curious to find out how Instacart’s data science team has adapted their program and tackled challenges they originally presented in 2019.

Based on a talk by Ishant Nayer, Senior Data Scientist at Instacart, watch the full video on DSSInsider and join me at the DSS Retail/Ecomm virtual experience.

What is Instacart?

Instacart is a retail and ecommerce company that offers grocery delivery and pick up services in the United States and Canada. You can utilize the service via their mobile app or website. Instacart operates as a four sided marketplace serving customers, retailers, third party marketplaces and the shoppers. You can select a variety of grocery, alcohol, healthcare and personal items. …

Natural Language Processing (NLP) is one of the most exciting fields of artificial intelligence that enables computers to understand human languages. NLP techniques are constantly evolving and promising applications are increasingly implemented by organizations to solve a wide range of problems.

What exactly are companies using NLP for? What are exciting NLP techniques in a practical context and what are the challenges when applying them?

We talked to thought leaders applying NLP in different industries about their favorite NLP techniques, the biggest trends, as well as opportunities and challenges of NLP in 2020. Here’s what they said:

What’s the biggest change you see in how your organization applies NLP recently?

“Training larger and larger models while data is changing constantly. The features we roll out are increasingly complex, which means that they often need larger ML models to support them, which in turn has consequences on infrastructure and training time. Simultaneously, especially with COVID, the information we need to be serving to users is changing constantly, which means we need to make sure our models are constantly updated. Luckily we’ve been able to adapt our development and data maintenance processes to accommodate frequent but longer training times, but it’s been quite a challenge to keep up.” — Christine Gerpheide, CTO at…

In advance of our upcoming event — Data Science Salon: Applying AI and ML to Media, Advertising, and Entertainment, we asked our speakers, who are some of nation’s leading data scientists in the media, advertising, and entertainment industries, to answer a few of our most pressing questions about the future of their industries. Read on for their insights — there’s some great advice in there!

What are some reasons a data scientist would want to move from another field into media/ad/entertainment?

“I’ve really enjoyed working in media because there are so many aspects of the company that data science can help with. I’ve been able to work on forecasting, operations research, user segmentation, natural language processing, content recommendations. Data science improves our readers’ experience with the Times but also helps with business concerns ranging from newspaper distribution to advertising sales. As the newspaper business continues to evolve with readers’ changing habits, I’m sure that the scope of our work will only increase.” …

Zoom calls, wine glass in hand, are the new normal, right? At DSS, we’re lucky to have a strong community of women in data science, and this community rallied around the idea of a virtual happy hour. But when it comes to sitting down in front of your computer or phone, can a happy hour with a bunch of people who don’t know each other actually work?

As opposed to friends or companies hosting a virtual happy hour where you know most everyone, our virtual happy hour felt a bit more like an in-person networking event, where people are in your network but not your immediate connections. …

Essential tips on building a solid community around your brand

I’m an entrepreneur of community. This means that my business and I are most successful when we look to connect others around common interests and problems. Developing a community allows you to position your brand in front of the right people at the right time, creating a memorable experience that makes your value clear and creates a memorable impact.

Building Community

It takes a lot of effort to build new communities, but not necessarily a lot of capital investment. New communities require a few things to be organized effectively: Knowledge, Time, and Proximity. …

As B2B marketers, we use conversions daily to define campaign goals and to ultimately lead to improved marketing ROI and closed deals. But how do we use just the right mix of data and science to improve conversions? This topic is bigger than just one question or even several answers, this topic requires a deep discussion, perhaps even a one day conference. I’ve been personally exploring this topic for quite a while now and the great news is that marketing and data science are moving forward more cohesively than ever before. …

Technology is changing our world. One way which this has occurred has been through the gathering and analysis of large amounts of data. For some, crunching numbers has never been so rewarding. We now can predict large tropical storms before they hit land, can estimate the likelihood of a disease outbreak, and can even trace how consumer sentiment shifts according to product releases and market changes. Sentiment analysis as well as text mining, can drastically change your marketing strategy by providing you with detailed information in ways that were once unimaginable. While sentiment analysis is not particularly new in marketing, the tools and precision with which we can carry out sentiment analysis have considerably changed. We used to only possess a handful of reviews or consumer opinions about a product. In some cases, we had around 50 to 100. It was possible to read them all and try to draw inferences from what we read. But nowadays, we have tens of thousands, and in some cases, millions of different consumer opinions. …

Data science is rapidly changing marketing. Specifically, contextual marketing is on the rise. Contextual marketing differs from traditional marketing. As its name suggests, this type of marketing strategy is all about CONTEXT. We are no longer interested in observing and predicting how people will carry out simple conscious-decision making. Instead, with this type of marketing, we seek to observe the habits that individuals get into when buying a certain product, booking a trip, or browsing through online catalogues.

Habitual patterns shape around 45 percent of choices that we make every day. Through contextual marketing, we get to discover and understand not only who someone is, but their geo-locations, what they are doing in different areas and points of time, and what they are most likely to do next. To be more precise, with the data available today, we can observe an individual’s age, gender, past behavior, device usage, location, weather conditions, time of day, and purchase history among other relevant factors. This helps us deliver the right message at the right time, and identify the right trends. Our ability to observe and assess deeply embedded contextual characteristics changes everything. …