“Beyond the Bot: AI for Empathetic Customer Support”
Presented by Canva
Customer support is no longer just about speed and automation — it’s about connection. At Canva, we believe that AI should enhance—not replace—the human touch that makes support truly meaningful.
In this challenge, you are invited to design an AI-powered solution that transforms digital customer support into an empathetic, emotionally intelligent, and helpful experience. Think beyond traditional chatbots. Can your AI detect frustration in a message and adjust its tone? Can it proactively offer help based on subtle behavioural signals? Can it act like a truly thoughtful assistant, not just a scripted responder?
Evaluation
This competition evaluates predicted spectra (μ_user) and corresponding uncertainties (σ_user) for different wavelengths against the ground truth pixel level spectrum (y) using using the Gaussian Log-likelihood (GLL) function.
The GLL values from each pair will be summed across all wavelengths and across the entire test set to produce a final GLL value (L). The final GLL value will be transformed into a score using the following conversion function:
We define L_ideal as the case where the submission perfectly matches the ground truth values, with an uncertainty of 10 parts per million (ppm) for AIRS and 1 PPM for FSG1. This ideal case is defined based on Ariel's Stability Requirement. For L_ref is defined using the mean and variance of the training dataset as its prediction for all instances.
The channels are weighted proportionally to the spectral channel width divided by the number of spectral points per instrument. Additionally, FGS1 weight has been doubled to emphasize its importance:
FGS1: 2 × (0.2/1) = 0.4
AIRS-Ch0: 1.95/282 ≈ 0.0069 per spectral point
The score will return a float in the interval [0, 1], with higher scores corresponding to better performing models. Any score below 0 will be treated as 0.
Price
Prizes
1st Place: $5,000
Top Student Group: $5,000 to the highest performing student team. A team would be considered a student team if majority members (e.g., at least 3 out of a 5 member team) are students enrolled in a high school or university degree. In the case of an even number of members, half of them must be students. A google form requesting proof materials will be shared at the end of the competition and Top Student Group will be selected from the application.