Shadowfax launches AI-based SF Maps for seamless deliveries

Shadowfax, India’s leading provider of cutting-edge e-commerce logistics solutions, has introduced SF Maps, an advanced Artificial intelligence (AI)-based address intelligence system designed to enhance delivery accuracy and efficiency.

The innovative tool predicts customer locations with unparalleled precision, setting a new industry standard with over 90 percent accuracy within 100 metres of the intended destination, says an official release. "SF Maps greatly improves navigation for delivery partners, thereby assisting e-commerce platforms and Direct-to-Consumer (D2C) brands in reducing cancellations due to address inaccuracies on their platforms."

Indian addresses often lack structure, are susceptible to language and understanding-based gaps and are highly prone to input error, posing challenges in pinpointing exact locations during delivery, the release added. "SF Maps addresses these complexities by leveraging a sophisticated AI/ML model trained on a vast dataset of Shadowfax’s past deliveries and pickups exceeding 1.5 billion data points. This model adeptly handles incomplete addresses, ambiguous area names, reliance on distant landmarks, and inaccurate pincodes, ensuring smooth operations. Further, precise navigation to customer addresses enables seamless deliveries without the need for additional calls, effectively reducing instances of missed deliveries and improving overall efficiency."

Since the introduction of SF Maps, Shadowfax has achieved a significant reduction in customer cancellations or return to origin (RTOs) by almost 10 percent and boosted customer net promoter score (NPS) by 25 percent.

Vaibhav Khandelwal, Chief Technology Officer, Shadowfax says: "SF Maps represents a significant leap forward in our mission to optimise the delivery speed and elevate customer experience while solving fundamental problems in last-mile logistics. This innovative AI model trained on our vast set of historical delivery data drives significant operational efficiencies for us. We deeply understand the problems that arise due to incomplete addresses and how it hinders further innovation, and hence we aim to make this AI model generally available for research in future.”

SF Maps uses an in-house artificial neural network (ANN)-based embedding model, trained using a Siamese network architecture, the release added. "The generated embeddings are fed into VectorDB and the extracted locations are passed through H3 geospatial indexing, further fine-tuning location intelligence. This custom-built model captures complex contextual relationships between address components and their geographical associations, leveraging deep learning algorithms to discern intricate patterns for more accurate location-based intelligence."

The feedback loop is powered by real-time delivery partner geolocations that Shadowfax captures every five seconds while they are on their platform. Shadowfax also deploys a WhatsApp-based conversational bot that interacts with customers and gathers address information for improved results and error correction, the release added.

So, how is SF Maps different or better than what3words, the global addressing system used in over 170 countries?

"In What3words (or Google Plus Codes), customers generate a unique code corresponding to their address location," says an official spokesperson of Shadowfax. "While placing the orders, they need to input the generated code and only then their location is available with the platform.

"Customers are more comfortable in sharing their address as a text. SF Maps is able to pinpoint lat/lng using these address texts. There is no need for customer or e-commerce platforms to integrate with a platform to get the location. Using SF Maps, it can be extracted directly using the address text inputted by the customer."