Ecommerce and online digital businesses spend millions of dollars attracting shoppers to their websites. Once they get there, the online shopping and buying experience must be seamless. Perhaps no stage in the funnel is more important than payment processing. Every intended purchase that can’t be completed results in lost revenue and customer churn.

To protect revenue and reduce lost sales, global ecommerce companies like Puma rely on Anodot’s autonomous payment monitoring solution. At a recent Merchant Payments Ecosystem conference, representatives from Anodot and Puma presented on the topic of AI-powered checkout optimization.

Michael Gaskin, Puma’s Senior DevOps Manager, uses Anodot to monitor the company’s 45 global ecommerce sites. Anodot’s autonomous business monitoring tool learns the normal behavior of Puma’s business metrics and sends alerts in real time when incidents are detected.

Anodot’s Customer Success Manager, Uriah Mitz, explained how payment incidents that would normally go undetected with traditional dashboards are flagged by Anodot’s AI-powered solution.

For example, shoppers on Puma’s website in Switzerland who were trying to use a gift card could not complete their purchase. With traditional solutions, this would be nearly impossible to notice because overall gift card purchases in Europe would appear to be at their normal level.

Anodot learns the normal behavior of every metric and dimension, down to granular levels such as individual countries, and can detect anomalies in near real time. Anodot sends an alert with insight into the root cause of the incident. In this case, API errors were causing the gift card payment issue.

Uriah and Michael ended their presentation with advice for any organization that wants to integrate AI/ML capabilities into their monitoring or analytics stack.

  1. Make data analysis and insights available to everyone. By sharing insights and alerts with account managers, operations and finance teams, you can increase efficiencies and time to remediate issues without reliance on analytics experts.
  2. Normal is never static. It’s difficult to alert on incidents with static thresholds. How long is too long since your last successful order? AI autonomously learns what is normal and answers this question for you across multiple websites.
  3. Focus on key metrics. You don’t need millions of metrics to monitor your core business. Built correctly, ten measures and a dozen dimensions would probably help you identify 99% of revenue-critical incidents.
  4. Measure the impact. Make sure you are monitoring business and not just technical metrics. Modern distributed systems are throwing errors all of the time but the business impact is often minimal or non-existent.

Whether you’re a merchant, acquirer, or payments processor, it’s crucial to have complete visibility into your payments ecosystem so you can identify anomalies in real-time, even through fluctuating demand. Anodot enables teams to optimize the payment process by monitoring the most granular payment metrics and identifying their correlations to each other.

Anodot’s AI-powered business monitoring solution delivers insight that often goes undetected by traditional dashboards that need to be constantly monitored. By dicing data into multiple dimensions, problems that aren’t known and trends that no one has ever seen become crystal clear.

Written by Anodot

Anodot leads in Autonomous Business Monitoring, offering real-time incident detection and innovative cloud cost management solutions with a primary focus on partnerships and MSP collaboration. Our machine learning platform not only identifies business incidents promptly but also optimizes cloud resources, reducing waste. By reducing alert noise by up to 95 percent and slashing time to detection by as much as 80 percent, Anodot has helped customers recover millions in time and revenue.

You'll believe it when you see it