Search

How LinkedIn uses AI/ML ??




Hello to all Community Members !!✨


Studying artificial intelligence opens a world of opportunities. At a basic level, you’ll better understand the systems and tools that you interact with on a daily basis. And if you stick with the subject and study more, you can help create cutting edge AI applications, like the Google Self Driving Car, or IBM’s Watson.

💫Before starting with core content lets see what exactly the AI and ML means:

🔹 Artificial Intelligence ( AI )

Only human beings have the special ability to think, make decisions, and Judgements on their own. It uses logic for it. Now, this is called human intelligence. But what if, we give these abilities like thinking, using logic, and taking judgments to a machine, then it would be called Artificial Intelligence.

Artificial Intelligence is a technique that enables the machine to act like a human. In other words, it is a system that can draw some useful conclusions about the surrounding world. The system is capable to take a decision on its own.

🔹 Machine Learning ( ML)

Machine learning (ML) is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.




🎯 In what ways does LinkedIn use AI?

So at LinkedIn, AI is like oxygen. They utilize AI and machine learning to optimize member experience across our product. And the reason are able to do that is due to the wealth of information they have about user, and the network assets that they have. So they have tons of information about users and their work history, and what they have done in the past, their skill sets, they also know who are the people you are connected to. Taking all of these network and identity assets and feeding them into this algorithm is what really makes AI and machine learning extremely powerful for LinkedIn experiences. So whether you are trying to recommend people that you should connect to, or you are trying to recommend you articles and updates that you should read in the news feed, if you are a recruiter, what are the candidates that you should be sourcing to fill up your roles? If you are a career seeker, what are the jobs you should actually apply for so that you can move ahead in your career? What are the courses you should take to really upskill yourself and prepare yourself for a better career? If you're a salesperson, who are the leads you should reach out to so that you can actually close a deal?

These experiences are much better with AI and machine learning, again, all based on the data, the richness of data that LinkedIn has. So AI really helps add more structure to all this valuable data that they have in their economic graph. And then take that and unleash it into all their product and create better member experience. So at LinkedIn, doing AI and machine learning for many, many years , started doing AI from 2007, in fact, "People You May Know" was their first AI product. And then "People Search", and since then they have been iterating on AI models for almost every single product experience have rolled out on site.

They also have a world class what we call A/B testing platform. So whenever roll out changes in AI systems, they are able to test the impact of the change by doing a side-by-side controlled A/B test. Using that mechanism, they've observed the impact to business, to product, through AI and machine learning has been significant .

They also use AI extensively to keep site safe ,So we use AI to detect fake accounts automatically, account takeovers, scraping, harassment, these are again all powered through AI. So although these may not look like usual applications of AI, but they're extremely important to really keep our site safe.


🎯Which AI and ML tools does LinkedIn use?

They take a hybrid approach, they have borrowed some tools from open source and they actually have also built some of the tools in-house to do machine learning and AI. So let's start with the infrastructure side. They use their own messaging system called Kafka. And this, in fact, this is open source and used by the entire world now. They have their own Hadoop clusters, they have their own data centers ,they have their own key value stores and own stream processing language called Samza, which is also open sourced and used by a lot of other companies in the valley and in the world. They extensively use Tensor Flow, which is something that been open sourced by Google for doing all our deep learning workflows. They use Spark with Scala extensively for doing data processing. They also some of Pig and Hive for doing data analytics. For online code, mostly use Java in most of online workflow. These are roughly the big tools which use at LinkedIn.

🎯How LinkedIn Uses Machine Learning in its Recruiter Recommendation Systems

In addition to nurturing one of the richest datasets in the world, LinkedIn has been constantly experimenting with cutting edge machine learning techniques in order to make artificial intelligence(AI) a first class citizen of the LinkedIn experience.

The recommendation experience in their Recruiter product required all LinkedIn’s machine learning expertise as it turned out to be a very unique challenge. In addition to dealing with an incredibly large and constantly growing dataset, LinkedIn Recruiter needs to handle arbitrarily complex queries and filters and deliver results that are relevant to a specific criteria. Search environments are so dynamic that result really hard to model as machine learning problems.

In the case of Recruiter, LinkedIn used a three-factor criterial to frame the objectives of the search and recommendation model.

1) Relevance: The search results need to not only return relevant candidates but to surface candidates that could be interested on the target position.

2) Query Intelligence: Search results should not only return candidates that match a specific criteria but also similar criteria’s. For instance a search for machine learning should return candidates that list data science in their skillsets.

3) Personalization: Very often, finding the ideal candidates for a company is based on matching attributes that fall outside the search criteria. Other times, recruiters are not certain of what criteria to use. Personalizing search results is a key element of any successful search and recommendation experience.

A fourth key criteria of the LinkedIn Recruiter search and recommendation experience that is not as visible as the previous three is its focus on simple metrics. To simplify the recommendation experience, LinkedIn modeled a series of key metrics that are tangible indicators of a successful recruitment.

Refer this for more information :

The AI Behind LinkedIn Recruiter search and recommendation systems

https://www.linkedin.com/learning/ai-the-linkedin-way-a-conversation-with-deepak-agarwal/in-what-ways-does-linkedin-use-ai


So here it is how LinkedIn use AI / ML ...hope you all like it 😊

Thank you for reading ✨
71 views1 comment

Recent Posts

See All