Beyond Toilet Paper – Essential Products with the Highest Demand Online

A look at best selling categories and brands in the US from a basket of “high priority” goods

Amazon recently announced that it would focus on “delivering items that are a higher priority [for] customers”, at the cost of less essential items, some of which are seeing delays of as much as a month.

This got us wondering – what are these “priority” items? How has demand for these products changed in the days and weeks since the world has been going into lockdown? And which brands have been at the forefront of this evolving demand?

While there isn’t a black and white definition of which goods are considered essential, according to one Reuters news source“Amazon considers baby products; health and household items; beauty and personal care; groceries; and industrial, scientific, and pet supplies as essential products.” We used this as a starting point in an endeavor to dig up answers to our questions. Here’s what we found …

Batteries, vitamins and dishwashing liquid are among the most sought after household products

Click here to read the rest of this article on the Semantics3 blog

Shopping for Hand Sanitizers Online in the Age of COVID-19

On 4x price increases, rapid price fluctuations, upstart brands and fake listings

COVID-19 has led to a spike in demand for products like hand sanitizers and face masks. Manufacturers of these products, many of whom were blindsided by this spurt, have been struggling to meet consumer needs, leading to empty supermarket shelves across the world. In the online world, this void has given rise to a different set of supply dynamics – since the barrier to introducing new products and dynamically altering prices is lower on ecommerce marketplaces, we’ve seen the emergence of new brands, new sellers, new products and a certain degree of predatory pricing behavior.

Consider the hand sanitizer category on the Amazon US marketplace. NONE of the traditional best selling brands and products are in stock. You’d be hard pressed to find any Purell or store brand Solimo goods that are in stock.


Click here to read the rest of this article on the Semantics3 blog

7 Elements of AI Product Strategy

A playbook for building ML powered products, teams and businesses

Building and selling machine learning (ML) products is hard. The underlying technology keeps evolving, requiring organizations to constantly be on their toes … and the rulebook on what makes for successful and profitable products is still being written, making for uncertain outcomes.

Over 5+ years of working with machine learning enabled products, we at Semantics3 have had to deal with many challenges stemming from the nascency of the industry. In this article, I’ve drawn from these experiences to distill a set of considerations for proactively anticipating and dealing with these vagaries. Being deliberate about these considerations has helped us align our products for long-term success.

The ideas below cover general trends; there will, of course, always be exceptions to norms.

#1 — What is the role of AI/ML in your product?

Quadrant A (Top Left): Standalone Black Box Products with ML Models at the Core

You’re selling a black box ML model, where customers determine how best to utilize the intelligence on offer (e.g. transcription services like Amazon Transcribe or Google Speech-To-Text).

If your product falls into this category, carefully think through the quirks of all the inputs that customers may send your way.

Click here to read the rest of this article on Towards Data Science

Predicting the Demand of Products Sold Online

Can the demand for an item be predicted before its market launch?

How about 1 month into launch, once the initial numbers are in?

Which signals best prophesy future demand? Can these be controlled?

We set out to answer the questions above using the ~10 billion price & demand signals in our database, and our Universal Product Catalog. Our approach was to build a forecasting model tuned to predict publicly available sales metrics such as sales rank.

Click here to read the rest of this article on the Semantics3 blog

Introducing Attribute Extraction from User-Generated Content

Attribute Extraction from ecommerce data – the generation of structured fields from unstructured text – is a popular product offering of ours. Our customers use it to improve the quality of their search catalogs, and thereby, their search relevance, faceted search and ad targeting.

Thus far, the scope of this product offering has extended to catalog data, primarily product titles, description and specifications. Now, we’re extending this capability to process user-generated content, including customer questions & answers.

Catalog Data
User-Generated Content

By distilling factual information from customer content, these algorithms can help boost the number and relevancy of structured attributes on popular ecommerce product pages. 

Click here to read the rest of this article on the Semantics3 blog

To Read Less — My 2020 Resolution

Each December, I religiously set a list of personal targets for the new year. Usually, the first item on this list is a reading target, and inevitably, the target is to read more than I did the previous year.

This year though, my target is to read less than I did the previous year… cue shock, horror, cries of blasphemy! What’s gotten into you Govind?

I’ll get to my justification in a bit, but first, a bit of a back story that I think many may identify with.

Like most people I knew growing up, I viewed reading as the noblest virtue, but one that I didn’t do enough of. At times, I’d get through a couple of books a week, but at others, I’d find myself staring at the same page for hours on end. I tried to be deliberate about making reading more of a habit, but I had many many stretches of downtime that I was quite self-critical of.

Click here to read the rest of this article on Medium

Shipping Line, Port and Route Dynamics of US Shipment Imports

This is the first in an article series in which we attempt to unearth dynamics of the shipping industry, by analyzing publicly available import shipment data in the United States.

In this article, we’ll take a look at market share dynamics for shipping lines – businesses that transport cargo aboard ships – and see how they’ve varied over the last few years. We’ll also look at traffic into ports in the US, origin ports from which the shipments leave, and the route links taken. The goal in exploring these questions is to understand market dynamics around key players, geographical locations and entrenched behaviors in the market, and trace how dynamics have changed through the years as market forces have had their say.

The answers to these questions come from an analysis of publicly available import data from the United States Customs and Border Protection’s (CBP) Automated Manifest System. This data spans approximately five years, and covers 180 million data points. Here’s what we found.

Shipping Lines

Click here to read the rest of this article on the Semantics3 blog

Using AI to Automate Web Crawling

Writing crawlers to extract data from websites is a seemingly intractable problem. The issue is that while it’s easy to build a one-off crawler, writing systems that generalize across sites is not easy, since websites usually have distinct unique underlying patterns. What’s more, website structures change with time, so these systems have to be robust to change.

In the age of machine learning, is there a smarter, more hands-off way of doing crawling? This is a goal that we’ve been chipping away at for years now, and over time we’ve made decent progress in doing automated generalizable crawling for a specific domain — ecommerce. In this article, I’d like to describe the system that we’ve built and the algorithms behind it; this work is the subject of a recent patent filing by our team.

The goal of our automated crawling project

Our goal in this project is to extract the entire catalog of an ecommerce site given just its homepage URL (see image above). This involves three key challenges.

Click here to read the rest of this article on the Semantics3 blog

Experiments with Shrinking my Garbage Footprint

I wrote this post back in 2017, but left it languishing in my drafts folder. Present day reflection at the end of this article.

“Garbage City”. The city that I live in, Bengaluru, has been conferred this unceremonious moniker in one too many articles of late. An increase in waste generation, poor waste segregation practices, non-operational processing plants and apathy from the citizenry has spawned a growing environmental and health crisis in the city, which has in turn affected the aesthetic beauty of the “Garden City of India”.

And the rest of urban India isn’t far behind. Mumbai, Chennai (link to a previous post on garbage in Chennai), Delhi and Kolkata face their own equally daunting challenges. “According to a World Bank 2015 report, India produces 109,589 tonnes of municipal solid waste a day which is projected to triple to 376,639 tonnes a day by 2025.” [Ref.]

Confronted with these terrifying facts, what is a concerned citizen to do?

Click here to read the rest of this article on Medium

Neutralizing Emissions from International Air Travel — On Project CORSIA and its Shortcomings

If you were to take a flight from India to the United States, to which country would the carbon emissions produced be attributed to? To India, since that’s where the flight took off? An equal split between the two countries? Or to all the countries along the route that the flight takes?

This is not just a hypothetical question. It matters, because it informs graphs like this:

Credit: Union of Concerned Scientists

And these graphs are in turn important, because they tell us where the clock on the metaphorical time bomb of climate doom stands. They determine the targets that each country needs to achieve to keep temperature rise below 2 degrees.

So which country is it? The answer is … drumroll …

Click here to read the rest of this article on Medium