Nadal or Djokovic? Could you predict the winner?



   



Most pundits will have an opinion on who will triumph in this year's US Open men's final - Rafael Nadal or Novak Djokovic - but the best insights into who will be crowned champion will come from the same technology that has helped cities to lower crime rates and plan for extreme weather.

Deep in the bowels of Arthur Ashe Stadium in Flushing Meadows, Queens, New York, beats the data heart of the 2013 US Open.

In a bland room accessed through an unmarked door, more than 60 laptops are piled high, arranged like a command control center for a mission to the moon.

This room is known as "scoring central", according to US Open officials.

It's where data is pushed to scoreboards on Louis Armstrong Court - the second largest US Open tennis court - or to TV screens across the globe.

But more than a power processing center, this is where the results of matches are broken down and analyzed, where it's determined not only who won, but why they won, according to the numbers.

"Say you wanted to see every backhand unforced error in a match. You would touch a button and all of those would come up," says IBM's vice-president of sports marketing, Rick Singer.

But seeing what has happened in past matches is rapidly giving way to better predicting what will happen in future pairings, explains Mr Singer.

To put it simply: the past might have centered around intuitively understanding that a player who gets a majority of their first serves in will win the match.

The future is pinpointing the exact percentile threshold the player must cross to win.

'Unusual statistics'

This year, IBM has gathered more than 41 million data points from eight years of Grand Slam tennis matches to better understand the small details that end up deciding a match.

Djokovic will win if he:

Wins more than 57% of 4-9 shot rallies
Wins more than 39% of first serve return points
Hits between 63% and 73% of winners from the forehand

Nadal will win if he:

Wins more than 48% of 4-9 shot rallies
Wins more than 63% of points on first serve
Averages fewer than 6.5 points per game on his own serve
Source: IBM

The idea is that by crunching more and more data, patterns will emerge that can help better hone predictions.

So what should Novak Djokovic do if he wants to beat a resurgent Rafael Nadal, who has emerged this summer as the dominant force on hard courts?

Looking at data from the head-to-head matches between the two in Grand Slams, IBM says that if Djokovic wins more than 57% of medium-length rallies (of between four and nine shots) then he will emerge triumphant.

He also has to win more than 39% of return points on Nadal's first serve.

Nadal, on the other hand, has to dominate on his serve. If he wins more than 63% of points on his first serve then IBM predicts he will win.

However, the longer Nadal's service games go on, the less likely he is to win. He needs to keep his service games relatively short, averaging fewer than 6.5 points per game, according to IBM.

"It's the same sort of statistical analysis and predictive analytics that we do for our clients all around the world, just applied to tennis," explains Mr Singer.

"What we're trying to do is find statistics that are unusual."

A backhanded solution

Djokovic, for instance, must focus on getting his backhand into play.

According to IBM's data, when Djokovic can hit his backhand deep to Nadal's forehand, his odds of winning the point dramatically increase.

However, during this tournament that stroke has been particularly difficult for Djokovic - he's had 32 backhand winners, but 70 backhand unforced errors.

For Nadal, he will go into the final knowing that his most powerful weapon - his forehand - is working well. He has hit 113 forehand winners, compared with Djokovic's 73.

He will also know that as long as he can continue to keep up his variety of serve, and go to the net occasionally - where he's won 81% of the points he has played there - he might have the upper hand over Djokovic.

Serbia's world number one will also have to improve his consistency in the final. Although both players have hit the same number of winners in the tournament so far (206), Djokovic has made 167 unforced errors, far more than Nadal's 130.

And with the Spaniard having dropped serve just once all tournament, Djokovic will have to be more ruthless when taking any break point opportunities that come his way, having converted only 44% up until now.

Elephant brain

It's only with the advent of big data technologies and faster, better, processing power that companies like IBM say they've been able to quickly and cheaply gather these new insights.

Most of these big data crunching technologies, from predicting airline prices to sports champions, use something known as Apache Hadoop.

Designed by engineers who had been working at Yahoo and elsewhere ("Hadoop" was the name of one of the creators' son's toy elephant), it is now just one of the components of IBM's predictive analytics toolkit.

The hope is that in the future, statistics like these might not just be of benefit to sports as a whole, but that athletes themselves will be better able to calibrate their performances.

"Each tournament we evolve a little bit further," says Mr Singer.

The goal, he says, is "to take the statistics beyond what people are expecting".

But for fans watching the US Open final who have no head for statistics, Rafael Nadal's coach and uncle, Toni Nadal, has this simple advice for what it takes to succeed: "You should play good, nothing else. You should play very well."


Click here for the article on the web.



<< Click here to see more recent news articles >>

 

 

Harnham blog & news

With over 10 years experience working solely in the Data & Analytics sector our consultants are able to offer detailed insights into the industry.

Visit our News & Blogs portal or check out our recent posts below.

Relocation Tips for Your Coast to Coast Move

Long before Microsoft held the tech fort in Washington, Boeing touched down. Rooted in tech, the Pacific Northwest has seen its share of hubs and does in fact boast the most jobs of the industry.  From the Big Apple to Apple’s HQ in California and Amazon’s orange smile in Washington State, the digital gold rush remains planted in the West. Not to be outdone, Google’s HQ and Microsoft square off as well in the Pacific Northwest. And like the Wild West, it’s a culture all its own. There’s no shortage of jobs, though Seattle, WA – desperately seeking experienced talent - and Portland, OR – work from home (WFH) opportunities - ply their workers in wildly different ways. Here are a few trends to consider as you debate if you should stay or go: Three Reasons to Make the LeapMake a Local Connection - The Silicon Forest, a play on California’s Silicon Valley, can be a bit intimidating to those outside the tech arena. But with a robust community of like-minded locals, groups, and events, it’s easy to find your tribe. Not interested in group functions? Not to worry. Portland boasts an abundance of remote worker opportunities to suit any personality.Get Your Resume Tech-Ready – With the rise of Applicant Tracking Systems (ATS), be sure your resume is laser-focused for a smooth transition. Even if you’re moving with a job already in hand, it doesn’t hurt to keep your credentials sharp. If you’re moving with family, helping them get their resume ready can ease their transition and job search as well. A Move to the PacNW Can Mean Lower Relocation Costs – Why? No sales tax. Well, not in Portland. On the flip side, Seattle doesn’t have income state tax. Either way, your check’s just a little bit bigger in the NW.Need more reasons to choose to move to the Emerald City of Seattle or the Silicon Forest of Oregon? Check it out here. TIME TO PUT A PLAN TOGETHER So, you've negotiated a relocation package, but you can't just pack up without a plan. What should be the number one item on your to-do list for your big move? Create a Budget – Moving costs can add up quickly. Whether you’ve been offered relocation assistance or not, it’s a good idea to have a budget so you know what to expect and can plan for any contingencies and unforeseen issues during your move. Include everything involved in a move, including packing boxes within your budget. Other things to consider?MoversGasLodging and Meals (along the way)o Grocery bills. Don’t forget,  you’ll also need lightbulbs, paper towels, batteries…all those little things which aren’t on your mind until you need them. Before You Can Stock Your Place, You Need to Find One – Finding Temporary or Rental Housing - While many companies offer temp housing until you can find more permanent placement, not everyone has that luxury. But, if the offer is made, take it. On the flip side, it can be difficult to find housing in an area you’re not familiar with, and can add to big move worries. However, there have been a few companies which have come online in the last few years to help with the housing search. One option, though, if you’re pressed for time is an AirBnB stay as many of them offer a discount for lengthier stays usually with a minimum of a month or more. Homeaway.com is another temporary rental option as is Sublet.com. Make All the Necessary Appointments as Soon as Possible - Try to organize your appointments and expected arrivals of furniture and such to happen on the same day or within a few consecutive days. This way, you can make your new boss aware of possible absences. They and their inbox will thank you.Start Building Your Network – Whether you’re looking to eventually by house, want to get setup in a new rental which offers a bit more permanence, or just want to know where the best restaurants are, and get settled into your new city, start building your network. Plenty of businesses offer get togethers at work, but consider building a network outside of your work life – go to meetups, attend local events, volunteer. Get in the habit of saying yes to new opportunities and activities. Making the effort can go a long way in enriching your new experience and helps to bring you more fully into experience your newfound digs. There is so much which goes into a move, whether its state-to-state, city-to-city, across the country, or around the world. But having a plan, making connections, and communicating openly with your new boss can help take some of the stress off moving. And whether you’ve negotiated a relocation package or are coordinating it on your own, there are plenty of ways to keep your eye on the prize and relax once you get to the other side and settled into your new job. Our brick-and-mortar locations are in San Francisco, New York, Berlin, and London, but we have clients around the world. Whether you’re looking for a permanent or a contract role, we’ve got you covered. Check out our current vacancies for opportunities or contact one of our recruitment consultants to learn more.  For our West Coast Team, call (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.   For our Mid-West and East Coast Teams, call (212) 796 - 6070 or send an email to newyorkinfo@harnham.com. 

The Culture Rush of Working in the Pacific Northwest

When you think of the Pacific Northwest, images of Pike’s Place at Seattle’s Waterfront and Starbucks’ birthplace may come immediately to mind. Or shoot down the I-5 Corridor toward the Silicon Forest, Oregon’s tech hub nod and nickname, a play on Silicon Valley just a little further South down the I-5 to San Francisco. One thing which may stand out immediately on the drive is the ocean vista view. Relax and unwind with a good cup of coffee at a local shop, bask in the mild climate, and curl up with a good book when you get a bit of free time. Here, the mantra is to ‘work hard, play harder’. The Land of Tech Seattle, also known as Emerald City, is one of the largest tech hubs of the eight in the US seeking top tech talent. Available jobs are outpacing the skilled workers to fill them. While they could outsource to other countries, many businesses are choosing to offer remote work options. Commuting Like a Local For most people, commuting involves keeping your car gassed up and maintained whether your office is a few miles down the road or in the next town. But, in the Pacific Northwest, commuting is part of an active lifestyle, while at the same time lowering your carbon footprint. How?  Well, with plenty of walking, hiking, and biking trails as well as a robust public transportation system, it’s a breeze to get to work. And you’ll be helping to support a sustainable environment as well. Biking is the most popular commuting option. If you’re a biker or plan to become one, be sure your outfitted with good reflective gear, a waterproof windbreaker, and of course, a helmet. If you’re going sans car, don’t forget a waterproof back. After all, you’ll need something to carry your stuff in, right?  Work/Life Balance Whether it's because of the temperate climate, the mild winters, or the laid-back atmosphere, the work/life balance in Washington and Oregon offer a peaceful setting to refresh and recharge. Available communities to spend time with like-minded people and the abundance of tech-focused jobs available in the area offer an amazing work/life balance. Spending Time in Nature – plenty of islands, parks, and trails offer a chance to commune with nature whether your commuting to and from work or planning for the weekend. The Arts - Portland and Seattle are both known for their arts and culture scenes including art festivals, indie bands, symphonies, museums, and more besides.Activities – From hiking to surfing to mountain climbing to yoga, there’s an activity for everyone to enjoy, meet people, and make friends.  One Final Takeaway… The quirky culture of the Pacific Northwest is an exercise in the unexpected. Whether listening to local bands, dressing up in costume at random, taking advantage of sunbreaks when the clouds part, or hiking in the rain, the reward is a good meal with good friends. If you’re new to the area, don’t be shy. Invite yourself along. Our brick-and-mortar locations are in San Francisco, New York, Berlin, and London, but we have clients around the world. Whether you’re looking for a permanent or a contract role, we’ve got you covered. Check out our current vacancies for opportunities or get in touch to learn more. For our West Coast Team, call (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.   For our Mid-West and East Coast Teams, call (212) 796 - 6070 or send an email to newyorkinfo@harnham.com. 

Computer Vision: Keeping an Eye on You

Computer Vision: Keeping an Eye on You

5 Animal Farm, Fahrenheit 451, and 1984 all wove tales of Big Brother watching. Remember when only Superman had X-ray vision and leapt tall buildings in a single bound? Well, as big tech grapples with the cause and effect of its place when it comes to facial recognition, security, and object detection, there’s a new superhero in town. Computer Vision.  The Eyes Which Sweep Our World While we still can’t be everywhere or see everything at once, we have eyes everywhere. Despite security cameras, motion detectors, satellites, computers, and smartphones, there are still dangers we may miss. So, by making our machines and computers visually-enabled using Artificial Intelligence, we significantly ramp up what we can see and how fast we can process it. Still growing, Computer Vision remains in an infant stage, given that autonomous cars still can’t differentiate between a rock and paper bag or worse, a person and a static object. Despite this, there are plenty of startups on the scene working toward a solution. As Artificial Intelligence increasingly blends with Biometric technology, it lends itself more easily to image recognition, allowing computers to correctly match fingerprints and facial patterns. But, no longer is it just matching two images. Now, it’s being taught to learn the difference between static images and liveness. This could prove invaluable for: Spotting weaponsSuspicious behaviorsDangerous object detection Safety Begins at Home With products such as security cameras prevailing within the security industry, businesses are hard at work creating and improving their products using the latest technologies.  One such company is working to boost the clarity of their home security cameras. Think grainy gray, blurry images from night vision options or overly bright and distorted in the day. Their camera chip will be HDR and will be able to take much clearer pictures even in low-light. At home, you might find this product in a doorbell camera which could prove quite useful for smart homes which offer the option of allowing service people into your home from a remote app on your phone.  And these cameras aren’t limited to your front door: ATMsIndoor/Outdoor camerasCCTV CamerasNumber Plate Recognition Cameras Though cameras have played a role in all of these areas for some time, the idea now is to keep them from being hacked and causing damage on both a product and a personal level. And like any type of Artificial Intelligence recognition system, these camera applications are created with advanced features to protect against hacking as well super speed processing of whether or not an object is an animal, a shadow, or some kind of inclement weather.  The best part? We’re only a few months away from products which can boost the benefits of many of available security cameras.  The Caveat of Image Recognition Systems More and more people around the world own security cameras, not the least of which is security personnel. With this increased level of ownership, the market is expected to have over $20 billion in revenue in less than five years. With such high demand, it’s no wonder only about five percent of footage ever gets viewed. But what if security professionals could navigate up to 80 video sources on a single server? What if the algorithms, analytics, and video processing worked with cameras of all types including, but not limited to:  Car dashboardsBody vestsDrone mounts With all these cameras surrounding us, the one thing to watch is that it is still humans who input the information the cameras use to process. When it comes to security professionals such as law enforcement, investigation, and government authorities its import to make sure the camera doesn’t discriminate or operate on bias. This an important issue even that even our most advanced intelligence agencies admits the algorithms for their facial recognition software are wrong about 15 percent of the time. However, one organization is working to improve and make these algorithms more ethically developed when it comes to image recognition as well as respecting individual privacy concerns.  As we navigate the growing pains of new technologies, it's important to understand these solutions are meant to ensure customers, the public, and communities can trust the solutions being created. If you’re looking for a new role in Computer Vision, take a look at our latest opportunities or get in touch with one of our expert consultants: For our West Coast Team, call (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.   For our Mid-West and East Coast Teams, call (212) 796 - 6070 or send an email to newyorkinfo@harnham.com. 

Can Robots Think Like We Do? Computer Vision May Provide The Answer

Can Robots Think Like We Do? Computer Vision May Provide The Answer

It might surprise you to learn that we, humans, and machines, learn in much the same way.  When we “size up a person, product, or situation” or “eyeball” a distance or measurement, our brain makes lightning quick calculations and guesses. From this, we’re able to reason and making relational assessments of separate items bound together by their similarities. These tasks, we accomplish as early as about 18-months old. This is what we’re working on getting computers to do as well, though we’re not quite there, yet. And just as children learn block by block and bit by bit, so too can we teach AI.  Computer Vision, when it comes to the industry of robotics, offers one of the most challenging aspects of the latest technological advancements. Keeping Up Appearances Humans take in, process, acknowledge, and understand information in order to act, but the replication of this human software has been challenging. One way in which companies are meeting this challenge is combine Computer Vision  hardware with software algorithms and Deep Learning to help teach computers to better “see” objects and identify them accurately. But like the inner-workings of the human mind, Machine Vision and Deep Learning touch on several areas such as actual and predicted Computer Vision  reporting, the three-pronged recipe of a Computer Vision  system, and a product development ecosystem which gets to the root of the technology. According to one report, Computer Vision in robotics is expected to grow significantly over a 7-year period. Some of the markets expected to see growth and making major investments include semiconductor manufacturers, software companies, and product developers. The Building Blocks The Deep Learning Engineer is to Computer Vision  what the Data Engineer is to Data Science. In both regards, these professionals must begin with a solid foundation and build from there. In order to achieve 100% accuracy, hardware and software improvements must get underway and are tantamount to a fully developed ecosystem of Computer Vision product development. Acceleration of this rapidly evolving industry is due to a number of factors:  Wide availability of wireless networks to millions of people worldwide.Deep Learning advances.More cost-effective chipsets.Images that can be processed, analyzed, and transmitted more easily with availability of high bandwidth.Open source libraries help to build differentiated products without reinventing the wheel every time when it comes to infrastructure. On the flipside, there are some barriers to overcome as well. These include, but are not limited to: Cost issues due to the fact that most advances take place in university research labs or big companies.A skills shortage of  hardware engineers with Computer Vision and Deep Learning experience.A lack of recognized applications for these products, though the closest attempt may be self-driving cars. Though these considerations may seem unsurmountable in the short-term, they do provide plenty of opportunity for those in design automation. From the initial analysis to servers in the cloud, and high-level solutions to help computers make informed decisions. Looking Ahead So, what happens when we teach computers to think as we do? Will there be a battle for domination of one species over another? Probably not. But one of the biggest challenges to get to the next level in automated machine learning is understanding how much our thinking process involves predictions. This is important in fields which must coordinate information based on exterior data. This type of learning has impacted a variety of fields from online shopping to medical diagnosis. The massive amount of data available for consumption is staggering. Not only are Deep Learning and Machine Learning products of corporate and scientific solutions, they are also being put in the palm of our hand; our homes, our cars, and our handheld devices in order to help us more efficiently complete jobs which might be too slow going or for which mistakes are prone. If you’re interested in industrial robotics and the AI space, we may have a role for you. We specialize in junior and senior roles and have numerous opportunities in Computer Vision. Take a look at our current vacancies or get in touch with one of our expert consultants:  For our West Coast Team, call (415) 614 - 4999 or send an email to sanfraninfo@harnham.com.   For our Mid-West and East Coast Teams, call (212) 796 - 6070 or send an email to newyorkinfo@harnham.com. 

Recently Viewed jobs