post

B2B product management

Artificial Intelligence (AI) & Machine Learning (ML)

Customer Research

Hardware

Digital Transformation

Our Privacy Policy is changing on April 5, 2022 - for more information and a description of the updates, <a href="https://mtpdevwpe.wpengine.com/privacy/" style="color:#FFFFFF;text-decoration:underline;">see the policy here.</a>

Switching back the focus from ‘Build only’ to ‘Build-measure-learn’

Product career special part 2: Making a change

Build what matters with vision-led product management

Lessons in fearless leadership

Building a product organisation from scratch by Kevin Mansfield

Footer About

Footer Contribute

Footer Get Involved

Footer Links

Mind the Product

Product Management

The executive product leader persona

Test blog post

Emily brings nearly 15 years of product management experience to her role as Managing Director for Mind the Product. While she has worked across a variety of industries, she will always have a soft spot for the travel industry where she spent most of her early career building software for airlines and developing a leading consumer travel app, TripCase. Emily is passionate about the craft of product management and loves talking about new ways to make products people love.

Emily Tate

<p>In this ProductTank San Francisco talk <a href="https://www.linkedin.com/in/alexmiller90/">Alex Miller,</a> one-time software engineer in the content understanding team at Yelp, gives us a case study of using machine learning (specifically deep learning) to provide a ranking system that surfaces the most beautiful photos of a business to the top of their page.</p>
<h2>Basic Photo Ranking</h2>
<p>You may know of Yelp as a site where users post reviews of businesses. But Alex tells us that the volume of photos is actually far greater than the number of reviews. Yelp wants to ensure the photos that best represent a business are featured at the top of a business’ page. So how do they do that?</p>
<p>Traditionally, Yelp used basic metadata to rank photos such as user feedback (like and votes), photo attributes (photo size, age), and clicks. While this worked up to a point, the underlying assumptions in the model were flawed. For example, a photo might get a lot of clicks because it was blurry and users wanted to see what it was. Or a photo might get a lot of likes because it was funny. But neither of these would be the best representation of the business.</p>
<h2>Helping the Model to Learn</h2>
<p>Yelp was looking for a model that could better understand the <em>quality</em> of photos: features such as depth of field, contrast, alignment, and other characteristics that are typically present in higher quality photos. So it started using a model called a Convolutional Neural Network (CNNs) that would provide a better predictor that photo would qualify as “beautiful”.</p>
<p>For any well-posed machine learning problem, Alex explains that you need a model and data to train that model. Yelp had to find “gold set” of photos that it could reliably say were good and bad to help the model learn. The content understanding team found a variety of signals that helped to determine a proxy: if a photo was taken by a DSLR camera, it would be labeled as “good”. If it was a non-DSLR camera, it would be labeled as “bad”. This allowed the model to learn the characteristics it was looking for as Yelp built its quality score.</p>
<h2>Putting the Model to Use</h2>
<p>Now that Yelp had a fairly reliable predictor of photo quality, the content understanding team had to decide how to use it in practice. Alex talks about other considerations they had to take into account: daily batch vs. streaming evaluations of photos, APIs that would be needed by other teams to use the ranking, and filtering and diversification logic to ensure the ranking would be a feed that would best represent a business on Yelp. In the end, they were able to evaluate the results with metrics and provide an impressive improvement in their feeds using a deep learning approach to evaluate photos.</p>
<div class="g g-21"><div class="g-single a-93"><a class="gofollow" data-track="OTMsMjEsMSw2MA==" href="https://mtpdevwpe.wpengine.com/product-management-training/public-workshops/communication-alignment-workshop/"><img decoding="async" src="https://mtpdevwpe.wpengine.com/wp-content/uploads/2022/04/Training-CA-layer-of-strategy-FOOTER-scaled.jpg" /></a></div></div>

core/freeform

Metrics don’t have all the answers: a human-centered approach to business strategy by Samihah Azim

Solving Ethical AI Problems, When Algorithms Go Wrong, and the Skills Needs To Work on AI Solutions: Insights From Kriti Sharma

How AI Is Changing The Product Management Job Description by Mayukh Bhaowal

Designing Meaningful Human Experiences by Kate O’Neill

Can AI Create a Fairer World? By Kriti Sharma

They’re Just Fancy Averages by Ben Fields

Data Science and Digital Businesses by Ali Gulez

Talking About Data Science by Jenessa Lancaster

AI at an Early Stage Startup by Zara Tam

Building Search Products With Machine Learning – Shakhina Pulatova

Using Deep Learning to Find Beautiful Photos by Alex Miller

ProductTank Abu Dhabi

ProductTank Manchester

ProductTank Newcastle Upon Tyne

ProductTank Milton Keynes

ProductTank London

ProductTank Jacksonville

ProductTank Phoenix

ProductTank Ljubljana

ProductTank Belgrade

ProductTank Bologna

ProductTank Edinburgh

ProductTank München

ProductTank Birmingham

ProductTank Porto

ProductTank Pune

ProductTank Chennai

ProductTank Genève

ProductTank Heidelberg

ProductTank Málaga

ProductTank Paris

ProductTank Hamburg

ProductTank Kraków

ProductTank Riga

ProductTank Reading

ProductTank San Francisco

ProductTank Montréal

ProductTank Goiania

ProductTank Des Moines

ProductTank Bangkok

ProductTank Canberra

ProductTank Dubai

ProductTank Valencia

ProductTank Madrid

ProductTank Düsseldorf

ProductTank Bucharest

ProductTank Raleigh

ProductTank Warsaw

ProductTank Bielefeld

ProductTank Bern

ProductTank Tokyo

ProductTank Pittsburgh

ProductTank Cardiff

ProductTank Krakow

ProductTank NYC

Product Leadership Course

ProductTank Recife

ProductTank Dublin

Member AMA: Unpacking User Research with Laura Klein

ProductTank Copenhagen

Trainer-Led Workshops

ProductTank Tauranga

World Product Day

Member AMA with Ken Norton

#mtpcon London+EMEA 2022 Workshops

#mtpcon London+EMEA 2022 Conference