August 2017 Summaries

In the August Changelog, improvements were made to the platform including adding Identity support for over 700 new institutions, bringing the total number of supported institutions to more than 1,000. Major banks like IBERIABANK, Simmons Bank, and Community Bank are among the newly added ones. Additionally, existing integrations have been upgraded for Dime Bank, Austin Bank, First Mid-Illinois, and over one hundred others. The data science team uses word embeddings and neural networks to categorize transaction data from more than 9,600 financial institutions, ensuring developers can provide great user experiences.

At Plaid, they collect data from over 9,600 financial institutions, creating a massive challenge in classifying ATM deposits, gas station refills, and other transactions into consistent categories. This consistency is crucial for customers like Coinbase, Lyft, or American Express to offer great products to all consumers, regardless of where they bank. The company's system uses machine learning to standardize categorization across thousands of institutions, tackling issues such as transaction categorization, ambiguous merchant names, and varying levels of accuracy across banks. A naive keyword-based approach was initially considered but proved ineffective due to the complexity of the task and the need for constant rule updates. Instead, Plaid employs a combination of machine learning techniques, including word embeddings and neural networks, to learn complex patterns in transaction descriptions and improve categorization accuracy. The system has achieved best-in-class accuracy and coverage despite the evolving nature of the underlying data, and Plaid continues to refine its approach through continuous retraining and experimentation with new model architectures.

In an update on their Identity product, Baker Shogry announces that coverage has expanded to over 1,000 financial institutions across the United States, including notable additions like IBERIABANK, Simmons Bank, and Community Bank. This expansion underscores the increasing importance of identity information in enhancing the financial technology ecosystem by enabling app developers to serve users better and combat fraud effectively. Despite some financial institutions' concerns about consumer access to identity information, the product facilitates more secure identity verification by allowing developers to match user-submitted data with verified details such as names, emails, and addresses. The announcement reflects the significant growth from the beginning of the year when support was limited to only 11 institutions, highlighting both the sensitivity and potential of this data. Current users of Identity automatically gain access to the expanded list of institutions, which is continuously updated in the API documentation.

We've continued upgrading integrations across the board, including KeyBank and Union Bank now supporting all products with longer transaction histories and faster account linkages. We've also introduced customizable copy in Link, allowing users to directly edit copy for various views. Additionally, we've improved webforms in the Support Center, providing more specific API identifiers for financial institutions and data issues, and enhanced our Support experience by designing custom webforms for each support category.