Looking for a perfect match-Why not try big data analysis this time?

1 of 18 people in US today use big data analytics in finding companionship.Couples are finding love online and online dating today has become a big business. Online dating sites combine "data" and "analytics" to help people find their perfect soul mate. The real hero behind the success stories of online love is the big data analytics technology and infrastructure that help people find their perfect life partner based on their stated preferences and behavioural matching. Big data dating is the secret of success behind long lasting romance in relationships of the 21^st century. This article elaborates how online dating data is used by companies to help customers find the secret to long lasting romance through data analysis techniques.

SQL Project for Data Analysis using Oracle Database-Part 1

Downloadable solution code | Explanatory videos | Tech Support

Start Project

According to Juniper Research, the market for dating through mobile apps is expected to rise from $1 billion in 2011 to $2.3 billion by 2016. If you are confused and want to find out whether a prospective date is a relationship material, don’t worry, big data analytics will help you. Relationships today are fuelled by data and powered by technology.Dating companies are leveraging big data analytics on treasure troves of information collected from the users in the form of questionnaires to provide compatible and better matches to their customers.

A couple of months ago an article was circulating on wired.com about how Chris McKinlay, a 35 year old UCLA Ph.D. graduate devised an algorithm to hack OkCupid by optimally using the data that was already there. McKinlay was not satisfied with the compatible match making algorithms the dating sites were using as it did not help him find his Mrs. Perfect with similar tastes who could become his soul mate. He devised a match making algorithm that suggested 20,000 compatible women with his tastes and preferences. After dating several women matching his compatibility percentage, he finally found his soul mate Tien Wang on his 88 ^th date. Technological innovations in big data paved for perfect match making online.

Image Credit: wired.com

Statistics on Online Dating 

Online dating statistics state that, of the 54 million singles in US, close to 40 million users have signed up with one of the popular dating sites like Match.com, OkCupid, eHarmony, Hinge or Tinder. Users of online dating websites spend an average of 22 minutes every time they visit an online dating website and close to 12 hours a week in online dating activities. 66% of the people have gone on a date with someone they have met online through these online dating sites.

New Projects

Llama2 Project for MetaData Generation using FAISS and RAGs

Loan Default Prediction Project using Explainable AI ML Models

LLM Project to Build and Fine Tune a Large Language Model

Learn to Build an End-to-End Machine Learning Pipeline - Part 1

Stock Price Prediction Project using LSTM and RNN

Langchain Project for Customer Support App in Python

Python and MongoDB Project for Beginners with Source Code-Part 2

Build an ETL Pipeline for Financial Data Analytics on GCP-IaC

LLM Project to Build and Fine Tune a Large Language Model

Llama2 Project for MetaData Generation using FAISS and RAGs

An analysis of online dating statistics shows that 1 in 10 Americans use a dating site and 25% of them have found their soul mates through these websites. Kelton Study in 2015, found that 1/3 ^rdof Americans (close to 80 million) people have used an Online Dating App or a site for finding their soul mate. Big data analysis has never been so amusing with millions of American singles pouring their hearts (and mobile phone batteries) out in search of true love.

Here's what valued users are saying about ProjectPro

I come from Northwestern University, which is ranked 9th in the US. Although the high-quality academics at school taught me all the basics I needed, obtaining practical experience was a challenge. This is when I was introduced to ProjectPro, and the fact that I am on my second subscription year...

Abhinav Agarwal

Graduate Student at Northwestern University

I think that they are fantastic. I attended Yale and Stanford and have worked at Honeywell,Oracle, and Arthur Andersen(Accenture) in the US. I have taken Big Data and Hadoop,NoSQL, Spark, Hadoop Admin, Hadoop projects. I have been happy with every project. They have really brought me into the...

Ray han

Tech Leader | Stanford / Yale University

Not sure what you are looking for?

View All Projects

According to the market research by IBIS world in 2014, Online dating industry in US is worth 2 billion dollars which has grown at the rate of 3.5% since 2008 and the Canadian dating industry amounts to $153 million. Juniper Research estimates that due to the excessive use of mobile phone apps, the online dating market is all set to rise from $1 billion in 2011 to $2.3 billion in 2016. With intense competition in Online Dating industry, companies are making every effort to maintain the credibility by matching the perfect partner to the perfect person at the perfect time.

Image Credit: ibisworld.com

Big Data Analytics in Online Dating

Match.com is 20 years old now that has helped create 517000 relationships, 92,000 marriages and 1 million babies. Match.com claims that it has more than 70 terabytes of data about its customers that helps them unlock the mysteries of their heart. According to eHarmony, 542 eHarmony users get married daily in US.

Image Credit: washingtonpost.com

The secret behind perfect match making by OkCupid (acquired by Match.com in 2011 for $50 million), Match.com and eHarmony is the big data analysis techniques behind the scenes.

In a world of data driven supremacy, it is not possible to connect people unless dating sites connect with online dating data. Online dating data is generally in the form of a questionnaire that helps users describe themselves about their likes, dislikes, interests, passions and other useful information. It is not a short questionnaire that you answer what is your favorite sport and color and the results help you find your life partner. The Online dating companies provide questionnaires’ of up to as much as 400 questions. Users have to answer questions on different topics varying from hypothetical situations to political views and taste preferences to increase their online dating success rate.

Image Credit: linkurio.us

Dating sites need to generate as much online dating data as possible for more probability of success in matching up partners who like each other. The questionnaire though helps in generating large datasets, there are still some weaknesses to the nature of online dating data collected through this method which makes big data analytics in dating more challenging. There is high probability that users might not be honest in answering the questionnaire or users end up providing inaccurate information unintentionally.

For example, females usually tend to lie about their weight, age and build while males might provide inaccurate information about their height, income and age intentionally. Another instance where a user might end up providing inaccurate data unintentionally is that he/she might believe that they love listening to classical music but the accuracy of this data can better be determined by analysis of the Spotify playlist or iTunes history.

Weaknesses in online dating data can lead to an incompatible match. Some of the dating websites are making efforts to generate online dating data for big data analytics by analyzing the behavior of users on the dating website based on the kind of profiles they visit. Few other dating sites employ collaborative filtering (preferences and tastes of several users are grouped into sets of similar users) to recommend dates based on their preferences and tastes.

The unpredictability of human behavior has made big data analytics the key to finding Mr. or Mrs. Right through online dating sites or apps because big data never lies .Online Dating data is collected from social media platforms, credit rating agencies, history of online shopping websites and various online behaviors like media consumption. Online Dating sites then apply big data analytics to the treasure trove of collected information which helps them determine the attributes that are attractive to online daters so that they can provide better matches and perfect soul mates to their customers. With sophisticated technology in place, Big Data Analytics promises to help you find true love via various online dating algorithms and predictive analytics by sifting through a store of “big data” of millions of user profiles.

How Online Dating Alogirthms work?

Online Dating giants like Match.com, eHarmony and OkCupid collect online dating data for big data analytics from Facebook profiles, online shopping pages to determine the likes and dislikes of a person as the data from these sites is much more helpful in predicting human behavior based on actions than what the users fill out in the questionnaire.

A McKinsey report states that “Companies must be able to apply advanced analytics to the large amount of structured and unstructured data at their disposal to gain a 360-degree view of their customers. Their engagement strategies should be based on an empirical analysis of customers’ recent behaviors and past experiences with the company, as well as the signals embedded in customers’ mobile or social-media data.”

Match.com provides its users with a questionnaire of 15 to 100 questions and then points are allocated to the user based on the pre-defined parameters in the system such as religion, income, education, hair color, age, etc. The users are then matched to people who have similar points.Match.com uses advanced big data analytics to find out any discrepancies in what people actually do on the website and what they actually confess. If any discrepancies are found, the match making algorithms adjust the compatible match results based on this behavior.

Amarnath Thombre, President at Match.com said- “ People have a check list of what they want, but if you look at who they are talking to, they break their own rules. They might list ‘money’ as an important quality in a partner, but then we see them messaging all the artists and guitar players.”

Match.com does not take any risk in determining the accuracy of online dating data for big data analysis.Match.com has started using facial recognition technology that helps them in finding out the “category” of matches that the user prefers and highlight the features that users are more attracted to.

Big data professionals at Match.com say that even if people are not so specific about the height, weight, hair color or race they definitely have some kind of facial shape they want to go for in their partner.Match.com aims to find a person’s type by facial feature analysis so that they can pair them up with the category of people who fit their type. These exclusive services cost 5000 USD for 6 months; however, Match.com is willing to pay the price as it gives them a sharper edge in competitive world.

With more than 565,000 couples married successfully and 438 people in US saying “I Do” every day because of eHarmony, the credit is owed to IBM Big Data and Analytics product IBM Pure Data System for Hadoop that renders personalized matches accurately and quickly.Statistics on Online Dating site eHarmony show that it generates approximately 13 million matches a day for its 54 million user base and altogether has more than 125 TB of data to analyze - which increases every day.

eHarmony asks it’s users to fill up a questionnaire of 400 questions when signing up which helps them collect online dating data based on physical traits, location based preferences, hobbies, passions and much more. Dataset of eHarmony is greater than 4 TB of data, photos excluded. The best thing is that the match making algorithms of eHarmony use all the online dating data it collects to find the perfect match for its users. The “400 questions” questionnaire is not the end. It collects data on the behavior of users in website such as how many pictures they upload to the database, how many times they log in, what kind of profile they visit frequently, etc. The data collected is sorted by specialized analysis algorithms which help users find a perfect match.

Jason Chunk, Vice President of eHarmony said -“ From the data, you can tell who is more introverted, who is likely to be an initiator, and we can also see if we give people matches at certain times of the day, they would be more likely to make communication with their matches. It kind of snowballs from there. We use a number of tools on top of that, as well.”

eHarmony uses MongoDB to ease the match making process for couples. Big Data and machine learning processes of eHarmony use a flow algorithm which process a billion prospective matches a day. The compatibility matching system of eHarmony was initially built on RDBMS but it took more than 2 weeks for the matching algorithm to execute.eHarmony has successfully reduced the time of execution by 95%( less than 12 hours) for the compatibility matching system algorithm to run by switching to MongoDB.

It is evident that big data plays a vital role in online dating revolution. Dating companies are harnessing the power of  big data applications to become perfectionists in helping people find true love online. As dating sites continue to collect tons of online dating data through different sources and refine their match making algorithms to harness the power of big data, we are not far witnessing the day when dating sites will know better than us on who our soul mate is.   

About the Author

ProjectPro

ProjectPro is the only online platform designed to help professionals gain practical, hands-on experience in big data, data engineering, data science, and machine learning related technologies. Having over 270+ reusable project templates in data science and big data with step-by-step walkthroughs,

Meet The Author