CIOReview
CIOReview | | 9 MAY 2024memorabilia. Many of our brands are known worldwide, such as PSA, PCGS, WATA, Goldin, and Card Ladder.I joined Collectors to help transform the company into a tech-first organization. We want to disrupt the industry, which currently is a market size of around $400 billion dollars, with next generation technology. Using that tech, we aim to transform the way collectors interact with and derive value from their collections, unlocking new possibilities for personal enjoyment, investment, and cultural preservation.Using Machine Learning To Iterate On a Traditional ApproachThis wouldn't be the first time that Collectors tried to create a price catalog for collectibles. Historically we created a few solutions that were based on statistical models, leveraging public sales data from various sources to generate highly-accurate price estimates. The problem is that only a fraction of collectibles are included in that sales data. Many collectibles are sold privately, and most don't even have a single sale because of the unique nature of collectibles.We decided to leverage machine learning to generate estimates for all collectibles. Machine learning is great at learning the hidden relationship between data points, which is exactly what we needed in order to generate these price estimates. In order to simplify the initial problem, we started with just trading cards. We developed a model and trained it with a data set containing cards and the prices they sold for. It would observe the relationship between each of the data elements, including the player, the team, the time of year, etc.Once trained, it could start to predict the value of any card with some level of confidence. Given a set of attributes, it would dynamically calculate the relationship between those specific elements and determine the value of a collectible with those specific traits. At first the confidence levels were lower, but as the team iterated on the machine learning model and expanded the data set that they were training the model with, the accuracy increased rapidly. Less than 6 months later, we increased the percentage of trading cards covered from 81% to 93%, and the number of medium-to-high estimates increased from 14.5% to over 60%!These estimates are starting to be used throughout our products. Besides helping collectors to understand the current value of their cards, we can now leverage these estimates within our internal operations across multiple parts of the company ­ for example to calculate the amount of shipping insurance we need when sending cards back to collectors, to determine the optimal starting bid for a consigned collectible, etc.Although this level of automation will allow us to make the operations more efficient, the larger benefit is actually for collectors themselves. By reducing the friction of our internal operations, this technology will help them to get their items back sooner from grading, and increase their confidence in the prices that they're buying and selling collectibles for. So far, it's helped thousands of our users to estimate the value of their collections and to determine the asking price for their collectibles in our new Goldin Marketplace.Pioneering This New Age of AINow that our machine learning and artificial intelligence capabilities team have completed this first set of features, we're starting to pursue the rest of our AI/ML roadmap. We're at the beginning of a new era ­ the Golden Age of Deep Learning Exploration. The tools are becoming increasingly accessible and advanced, limited only by the speed at which we apply them toward new problem sets. Equipped with the right outcomes in mind, you and your organization can revolutionize the state of technology in your industry and unlock new value for your customers. With our tech, we aim to transform the way collectors interact with and derive value from their collections, unlocking new possibilities for personal enjoyment, investment, and cultural preservationDan Van Tran
< Page 8 | Page 10 >