Tech on the desk

Sometimes, love is precisely figuring out simply how improper issues are going within the partner’s newest challenge. Megha Gambhir put the determine at “95 percent”.
Her husband, desk tennis coach Deepak Malik, was boggled over why his younger ward Wesley do Rosario’s southpaw benefit wasn’t translating into extra victories with depraved enjoying angles, although he intuitively knew what was tousled.
It was as a result of – Megha would inform him calmly after a loss – the boy was not focusing on the acute forehand nook and enjoying throughout to the opponent’s consolation zone on the backhand. And shedding velocity on the ball alongside the way in which.
“She said 90-95 per cent of his returns were sent wrong even as the ball quality reduced. It was an eye-opener to be pinpointed to the exact problem!” Deepak exclaims.
Having nailed the error in a video evaluation, the Goan junior would certain out of the also-ran grade and make the nation’s Top-4 within the subsequent 5-6 months, having repaired a bunch of different tactical errors. Megha, a pastime shuttler when younger however an intrepid techie with Artificial Intelligence professional Anand Hariharan, had helped with one other piece of the jigsaw to ship yet one more aspiring paddler on his method.
This final week, Stupa Analytics, of which Megha is the CEO, tied up with the International Table Tennis Federation (ITTF) for performance-analytic instruments making them obtainable to 226 member international locations. ITTF reckons 30 million play the game professionally internationally, making it a 1 billion market. And a easy follow video shot on a phone can throw up a plethora of information – from nature of factors received on service, lengthy & quick size conversions, forms of errors & winners, clusters utilizing ball warmth maps, development of ball velocity, video highlights backing knowledge, stroke and hand-type evaluation.
Table tennis, a sport that’s leaving its bashful presence amongst racquet sports activities behind with daring sponsorship partnerships with Coca Cola final 12 months, is leaping into digitalisation of its participant knowledge – first with on-line teaching by way of Pingprofy and now AI analytics with Stupa.
Circa 2018, Megha had watched her husband and former cadets nationwide coach Deepak agonise over a follow video, sitting with pen and paper and manually dissecting a participant’s sport.
Modest starting
Circa 2018, Megha had watched her husband and former cadets nationwide coach Deepak agonise over a follow video, sitting with pen and paper and manually dissecting a participant’s sport. “I would sit with Excel sheets and jot down the percentage of strokes and winners, strengths and patterns in tactics,” he remembers.
Megha, with fruitful tech consultancy stints at HCL, Cognizant, PepsiCo and Ernst & Young, was itching to begin one thing of her personal, when Deepak would request her assist to design a software to ease his workload.
Starting out with incremental tables, albeit with handbook knowledge extraction the place a match would nonetheless take 4-6 hours, she would rope in AI professionals to efficiently scale up a mannequin to analyse.
The Rohtak-born coach, who had picked up the game in Class 8 over his mother and father’ pal’s eating desk, was now serving to greater than his dozen wards to learn their video games higher, and plan follow classes in Delhi. The sport was additionally the explanation the couple met. “I got admission into Hindu College in Delhi only on the basis of my sports quota. Without TT, it was impossible. We met there,” Deepak remembers.
A bit geeky, he would shun all of the emotional rollercoasters of sports activities biopics to give attention to how the coaches labored in motion pictures. “I watch every sports movie to observe the coach. But the one that sparked this idea was Miracle (2004), about USA’s Winter Olympics ice hockey win over Russia. I wondered if they could use data back in 1980, why aren’t we doing it in TT now?”
Megha would carry alive his obscure concept by assembling a staff of (now) 20 IT and sport analysts, because the product helped them crack offers with particular person federations from US, Portugal, Hungary and Sweden.

Big breakthrough
Ball monitoring together with ball velocity posed probably the most tough issues for AI to resolve by way of a cell digital camera. “Evolution of this feature was simply a roller coaster… as at many steps we felt it is difficult to achieve but the persistent effort of Anand Hariharan, our chief AI Architect, along with the passionate team led to the big breakthrough…. it is simply amazing to see ball speed and tracking just on the mobile. The second insight which we had fun developing is something that we are doing now – auto suggestion and predictions,” Megha says.
Back dwelling, 21-year-old Surat lad Manav Thakkar would profit early. At the 2019 Senior Nationals semifinal in opposition to G Sathiyan, Deepak would take Thakkar to the venue at 6.30 am, and over the following 4 hours use the freshly-culled knowledge to arm him with a shock weapon. Playing nearer to the desk, when trailing 5-9 within the decider, Thakkar would blitz the following six factors on a bounce-changing technique to win the match. “He’d never taken even a game off him (Sathiyan) before. But data helped us devise the strategy,” Malik says.

Plans for the long run
Megha is aiming larger, nicely conscious that the East Asian powerhouses are masters of the sport. “We know China, Japan, Korea have their sophisticated in-house analytics and they have been recording opponents extensively. But Stupa will open this up not just to Indians, but also North America and Europe. If more players become self-aware and get data-driven insights, it can optimise training and raise levels,” she muses.
Personally, she’s eager on forays into badminton, squash, tennis in addition to billiards, snooker and pool at a later date. “I didn’t start out as a TT player, but I was keenly interested and travelled to tournaments to understand the sport’s working,” she says. Two analysts are actually fully into AI-based knowledge – a plug-in digital camera information the match, video goes on Cloud, and outcomes are delivered inside minutes.
Work on an angle -agnostic software program is underway. And movies might make method for sensor-based evaluation. “We’ll go deeper. So, make it so nuanced that it can identify a forehand topspin push chop from something that’s very close to it in action, but lands differently,” Megha says.
Tournament websites, broadcasters in addition to betting websites will have the ability to entry the information for stay streams and graphs, from ITTF’s a number of engagements. What the husband-wife duo although is aware of minutely is that each one of it hinges on how the backroom work seems to be within the foreground. “Execution is all-important,” she says.