Restaurants on busy thoroughfares can use many elements to catch a customer’s eye, but online ordering experiences mostly rely on the menu to generate sales.
Category Archives: AI & ML
Solving for Unobserved Data in a Regression Model Using a Simple Data Adjustment
Making accurate predictions when historical information isn’t fully observable is a central problem in delivery logistics.
Multiplicar por 4 la capacidad de los experimentos en línea gracias a la paralelización y el aumento de la sensibilidad
Las empresas impulsadas por los datos miden las reacciones reales de los clientes para determinar la eficacia de las características de los nuevos productos, pero la imposibilidad de realizar estos experimentos simultáneamente y en grupos mutuamente excluyentes ralentiza considerablemente el desarrollo.
How DoorDash is Scaling its Data Platform to Delight Customers and Meet our Growing Demand
Today, many of the fastest growing, most successful companies are data-driven.
Leveraging Causal Modeling to Get More Value from Flat Experiment Results
A/B tests and multivariate experiments provide a principled way of analyzing whether a product change improves business metrics.
Retraining Machine Learning Models in the Wake of COVID-19
The advent of the COVID-19 pandemic created significant changes in how people took their meals, causing greater demand for food deliveries.
Apoyo a la iteración rápida de productos con una plataforma de análisis de la experimentación
La nueva plataforma de experimentación de DoorDash, basada en una combinación de SQL, Kubernetes y Python, permite una rápida iteración de mejoras de funciones basadas en datos.
Using a Human-in-the-Loop to Overcome the Cold Start Problem in Menu Item Tagging
Companies with large digital catalogs often have lots of free text data about their items, but very few actual labels, making it difficult to analyze the data and develop new features.
Building a system that can support machine learning (ML)-powered search and discovery features while simultaneously being interpretable enough for business users to develop curated experiences is difficult.
Optimización del gasto en marketing de DoorDash con aprendizaje automático
Over a hundred years ago, John Wanamaker famously said “Half the money I spend on advertising is wasted; the trouble is, I don’t know which half”.
Eficiencia en el servicio de modelos de aprendizaje automático minimizando la sobrecarga de la red con gRPC
The challenge of building machine learning (ML)-powered applications is running inferences on large volumes of data and returning a prediction over the network within milliseconds, which can’t be done without minimizing network overheads.