Bengaluru-based startup Latlong has claimed that according to a study conducted by IIT Kanpur, their geo-coding API is twice as good as Google Maps API.
Latlong said in a blog post, citing Prof. Onkar Dikshit of the National Centre of Geodesy at IIT Kanpur, that the accuracy of its API is 35x better than that of Microsoft Bing API and nearly 200x times better than that of TomTom API.
Puranika Narayana Bhatta, CEO at Latlong, took to Twitter on the recently released geo-coding API. "A few months ago, while driving in interior Karnataka, we had to go from a small village to Goruru, on the banks of Hemavathi. Son opened Google Maps & started directing. In a couple of kms, sensed we were off. Stopped the car,checked the map; we were headed to a wrong ‘Goruru’," he said in a tweet.
"After returning, conversation ensued with Rahul, our CTO, on how to use our intuitive knowledge about place names. He brought up a more important point: people view addresses telescopically down (country to house number) while addresses are written microscopically upwards. Order in address string impacts conversion to a point (lat-long coordinates) in a big way. So, we decided to translate our ‘tribal’ knowledge to APIs in our platform, with the objective to beat average accuracy of world’s leading maps APIs from Google, Microsoft Bing and TomTom," he added.
A few months ago, while driving in interior Karnataka, we had to go from a small village to Goruru, on the banks of Hemavathi.
Son opened Google Maps & started directing. In a couple of kms, sensed we were off. Stopped car; checked map; we were headed to a wrong ‘Goruru’. (1/n)— Narayana Bhatta (@BhattaPN) March 10, 2023
Bhatta told Moneycontrol: "We have curated data of pincodes, areas, RTOs, sub-areas, neighbourhoods etc so we could quickly narrow down a particular area so it is much more accurate than Google Maps".
"A benchmarking exercise was carried out using around 4,600 addresses including residential and businesses, hospitals and schools, cities and villages, tier 1 and tier 4 cities and apartments and individual houses. Latlong’s strength is having curated area data (polygons in maps), across India. This helps eliminate all the non-fitting locations very quickly, as they don’t fit into the ‘area’. Latlong uses Indian language scripts appropriately for string matches. For example: Jainagar/Jayanagara/Jayanagar all map to the same location with the help of IIT Madras's AI4Bharat’s API," he added.
IIT Kanpur was unavailable for comment.
Discover the latest Business News, Sensex, and Nifty updates. Obtain Personal Finance insights, tax queries, and expert opinions on Moneycontrol or download the Moneycontrol App to stay updated!
Find the best of Al News in one place, specially curated for you every weekend.
Stay on top of the latest tech trends and biggest startup news.
