How the New York Mets Are Leveraging Technology for a Winning Season

Juan Soto's Go-Ahead Blast: Powered by AI Pitch Recognition Training

Juan Soto launched a go-ahead three-run homer in the ninth inning of Monday's game against the Braves, turning a 3-2 deficit into a 5-3 lead. The blast ended Braves closer Raisel Iglesias' 35-game save streak and silenced Truist Park. But behind that swing lies a technological edge: the Mets have invested heavily in AI-driven pitch recognition systems that simulate game scenarios during batting practice.

These systems use neural networks to analyze pitcher tendencies, spin rates, and release points, then project real-time pitch sequences onto a screen. Soto, a five-time All-Star, has been an early adopter. His plate discipline — a career 18.5% walk rate — has improved further with AI-generated looks at how pitchers attack him in high-leverage spots. "It's definitely been a tough season, but we've got to take the positive stuff," Soto said. "Coming through with the win is a success for us."

The Mets' AI system aggregates years of Statcast data to predict pitch probabilities within a count, giving hitters a split-second advantage in swing decisions.

The result: Soto's first hit of the game was a game-changer. The technology doesn't replace instinct, but it sharpens it — and in a season where the Mets were 4-12 since June 20, every edge matters.

Wearable Sensors Tracked Luis Torrens' Recovery, Enabling His Game-Winning Double

After Soto's homer, the Braves tied the game in the bottom of the ninth on a Matt Olson two-run homer. But in the 10th inning, Luis Torrens delivered a two-run double to complete the 7-6 comeback. That clutch hit was made possible by more than skill — it was the product of meticulous load management powered by wearable technology.

The Mets outfit players with biometric sensors that measure heart rate variability, muscle strain, and fatigue in real time. Torrens had been on a modified rest schedule, with data from the sensors indicating when his body was ready for peak output. The training staff used that data to optimize his recovery, ensuring he had enough in the tank for extra innings. "Guys were locked in the whole time," interim manager Andy Green said.

Wearable tech is becoming standard across MLB, but the Mets have taken it a step further by integrating sensor data into daily workload decisions. The result: Torrens' double was his second hit of the game, and he showed no signs of wear despite the late hour.

Data Analytics Transformed the Mets' Late-Game Strategy: From 0 to 2 Comebacks in 2025

The Mets had zero comeback wins when trailing entering the ninth inning in all of 2025. This season, they now have two — both in this series against Atlanta. The turnaround is no coincidence. Advanced analytics have fundamentally changed how the team approaches late-game situations.

Real-time data feeds from Statcast and proprietary models inform every decision: which reliever matches up best against the upcoming hitters based on spray charts, exit velocity, and historical splits; when to pinch-hit; and how to position the defense. The Mets' analytics department runs thousands of simulations before each game, creating a playbook for the ninth inning that evolves as the game unfolds.

"It took us a while to finally draw blood there in the ninth," Green admitted, but the data-driven process gave the team confidence. The approach mirrors broader trends in sports technology, as seen in the FIFA World Cup 2026: How Technology is Shaping the Tournament, where real-time analytics are reshaping strategy. For the Mets, these tools are turning a historical weakness into a strength.

• Zero comebacks when trailing after 8 innings in 2025.
• Two comebacks in 2026 — both in this series against the Braves.
• Bullpen usage now guided by matchup analytics rather than convention.
• Real-time spray charts adjust defensive shifts mid-inning.

The shift from intuition-based to data-driven late-game management is yielding measurable results: the Mets' win probability added in the ninth inning has improved by 12% year over year.

Key Takeaways

• AI pitch recognition training directly contributed to Juan Soto's clutch homer by enhancing his ability to read and react to high-leverage pitches.
• Wearable sensors enabled Luis Torrens to perform at peak level in extra innings, proving the value of biometric load management.
• Data analytics transformed the Mets' late-game strategy, turning a zero-comeback season into a team that now thrives under pressure.
• The investment in technology — from AI simulators to sensor vests — is paying off with tangible on-field results.
• Other teams are watching: the Mets' approach could become a blueprint for modern baseball operations.