AI in Marketing


Hello world it’s Siraj and AI in marketing. That’s the topic for today’s video I want to start off this video with a demo and what this is is an AI Writer. what it does is it takes in as input a keyword in my case, I’ll say it’s gonna be wine, okay So I want to write an article about red wine I’m gonna send it to my email address It’s gonna use an AI to then generate an article based on that it might take a few minutes It might take a few hours But luckily I already have the output right here for us what it does is it because it’s gonna generate text Based on that keyword and it’s gonna use its sources are going to be the internet so it’s going to Search the internet for other related articles on the topic It’s gonna take all that text and compile it into one giant Text data set, it’s gonna feed that into its AI model which is likely an LS TM neural network. Don’t worry if you don’t understand that, I’ll talk about that later in the video And then it’s going to output an article that we see here. This could be a very compressed article low compression It could be a very medium or a high compression article and they can get pretty good, okay Pretty damn good, so good in fact that it’s very likely that you’ve already read an article or seen some kind of data That was created entirely by an AI and you didn’t even know it Very famous brands from Fox to Yahoo to The Associated Press all use AI to generate content And that’s just one of the ways that AI can be used in both marketing advertising and the entire marketing funnel the pipeline so in this video I’m going to talk about ways we can do that and at the very end we’re going to look at some code for different Architectures that we can use to do this ok, so let’s start off with The ways that AI can be used in marketing, right so one way is through audience targeting right so if you have some startup a company a brand you have an audience of Customers right and if you have some new product you want to target the specific subset of your customers they’re going to be most willing to convert into sales You don’t want to waste your time your energy your money your resources on customers who won’t convert right and so How do you target those exact customers that would be most likely to convert? This is a perfect use case for AI and we’ll talk about that in a bit The second part is content creation right if you’ve already Targeted those users that are most likely to convert to sales for your product How are then you? How are you supposed to generate content? That would be best suited for them the ideal, the easy way is to get a human to do it But could you get an AI to do it is the question and the answer of course, is yes And we’ll talk about that as well. Now real time optimization is another strategy using AI Let’s say you have some marketing campaign let’s say it’s an email campaign, right and you’re constantly setting ads out to your users to see how they feel about the product and You’re getting feedback from them. Whether they like it or not how do you optimize that content or route in real-time so that you’re learning from what your users like and what they don’t like and This has been happening like I said for a very very long time and we’re gonna learn how in this video So some b2b marketers were asked. What are these metrics that indicate successful return on AI investments and across the board that the number one way with 59% of respondents saying this was that it gives them better close rates for sales so sales equates to revenue and revenue is the lifeblood of any company right, you can’t have a company if you don’t have revenue. Okay, so if I didn’t have revenue. I couldn’t hire people. I couldn’t make videos for you I couldn’t live I’ve got revenue, okay So and I am using AI to help target my content So I myself in and mitting that I’m using AI to help target, and you know make sure my content is as Targeted as possible And they say in the end if you have some product that you’re selling it’s going to then help close the rates for sales Right for me for me. That was my decentralized applications course That was my only paid offering up to this point, and I targeted it very well, and it resulted in some good sales We’re just gonna help me grow the business later on So AI can be used for that as well So let’s talk about some startups in the space that are helping to move this field forward right so Appier is one example. This is a Taiwan based company and What they do is they predict what audience members are likely to do next right so if you have some products right you’re some ecommerce Website and you’re selling shoes, and you’re selling all sorts of clothing Let’s say if a customer buys shoes, then it is likely that the customer won’t buy another pair of shoes But it is likely that they’ll buy a pair of socks to complement those shoes How can you predict what the customer is going to do next and what they do is they provide AI as a service to companies? To allow them to predict, what customers are going to do next? Another example is drawbridge, right? so users switch devices all the time right so they can be on mobile they can be on a desktop they can be on a ps4 and ideally we can talk we can target the type of Content to the specific device that they’re on at the time, and so that’s what drawbridge does it predicts What times that a user is going to be on a specific platform? And then it allows a brand to create content base on that platform another example is insidesales.com Right so if you have a lot of prospective sales You can’t just target all of them because you’re gonna be wasting time and energy and money on targeting this giant segment of users When it turns out that the the customers that are most likely to convert are probably only 20% And that’s what Inside Sales does is it helps you find that 20%? of your customer base that are gonna be the most likely to convert to the sales for your product that you’re pushing and there’s one more. I want to talk about it’s called Persado and what they do is they will Help you create content It will help you find the phrases and the words that’s going to drive the greatest action for your audience that convert into sales So you could say you know a text message in this way But if you say it in this way you reword it a little bit It’s going to increase sales by this much And this is something that we humans try to do we use our intuition right so you know Don Draper from Mad Men He comes into the boardroom. He’s like this is gonna work, and then it works, and it’s beautiful That’s not how it works anymore if you don’t have a database decision. What are you doing right so? Really, good marketers and really good. You know sales people an advertiser, not sales advertiser’s tells people as well But not in this case use AI to make decisions. Okay. It’s not just about intuition alone. You’ve got to use it You’ve got a base your decision on the data. If you don’t got the data. You don’t got sh… anything right so shit so anyway, so Let’s start with audience targeting right so how do we target some segment of the audience? That is gonna be most likely to convert for a given ad and then focus all of our time and energy on that segment So we could think about this as a recommender system problem right so a bunch of sites use recommender systems Amazon Netflix You know everybody uses it these days and one very common way to build recommender systems is to use matrix factorization Okay, so here’s how it works if you have some product and in this case we’re talking about marketing so our product is going to be a an ad right so you have a bunch of ads you’ve tried out and the users rated all of those ads on a Scale of one to ten and what this turns out is you have a giant matrix of users and Ads and their ratings for all of those ads so it turns out that those users aren’t going to rate all of those ads They’re only going to rate some of them So what we do for matrix mean factorization is we decompose this giant matrix into two different matrices One is going to be how a user’s rates certain features of an ad the other is going to be how? Certain features are rated by users for a specific ad so two different matrices the process of decomposing this matrix into a two different feature matrices is a Type of machine learning using neural networks or SVD is but I’ve talked about that before If you search Siraj recommender system on youtube you’ll find a bunch of videos there, but I want to give you a high-level Explanation here once. We’ve decomposed that giant matrix into these two smaller matrices We then use the dot product to combine them again in such a way that all of those blank spaces are filled right so what? We’re trying to do is we’re trying to find those blank spaces If a user has rated a certain ad this way and another ad this way How would they rate this ad and so this is a prediction, this is what the AI is doing using me factorization? And so a popular library to do this has been LightFM I’ve made a video on that before where it takes it generates user and item representations by functioning as a factorization machines and Learning the linear embeddings for each feature it then takes a dot products of each of these two representation vector and gets a score But with deep neural networks We can improve on this by creating more meaningful Representations right deep neural networks outperform all other machine learning models when it comes to learning features, ok so when it comes to learning features deep neural nets blow everything else out of the water if we have enough data and computing power and so TensorRec is a Library that has a lot of developer activity and I highly recommend it built on top of tensor flow That does this, it allows us to use tensor flow to build deep neural networks for Recommendation engines this could be to recommend the optimal ads for your users to recommend products to recommend whatever it is Now ideally if you’re a brand if you’re a company you’ve got some data Set that shows How users feel about certain ads you’ve done in the past and based on that you can create new ads that a certain user would be likely to convert on so you have to make sure you have that data If you don’t have that data your startup you want to build a service for brands than just Google data set For data set ad campaign and then test it out from there But the idea is that going beyond matrix factorization we can build neural networks to do this Right and so the process is very similar in that we are learning to matrices And then we’re performing a dot product between those two matrices To create predicted scores for a given user and then we just read off of that matrix to predict what a certain user would score a particular ad and then if we have some threshold like if a user scores would score above an Eight out of ten for this ad then deploy this ad to them if it’s under that then deployed this ad to them okay So it’s kind of like that so there are four steps in this process The first one is to transform our input data into feature tensors for easy embedding right we have some input data That’s a giant matrix, and then we use Pandas say to then convert that into a data frame object And once we do that we convert them to feature tensors using an algorithm like Word 2 Vec which we could use in one line of code or Several other ones and then once we have that we transform the user item feature tensors into user item representations we transform that pair into a prediction and then transform that prediction and truth value into a loss Value for a loss function minimize that using gradient descent until we have reached a minimum minimal loss function value And then we can use that model to predict what a certain user would like so here is a very simple programmatic example of us using TensorRec to Recommend users a specific type of data This could be ads it could be anything right so we build the model in a single line That’s all we imported. We generate some dummy data. We fit them up model on that data. We predict What the scores would be would be based on the given data, and then we use a percentage recall as a Evaluation metric to see how good it’s doing on testing data set that’s it. TensorRec check it out Now, once we have targeted a specific subset of our users that we know exactly We’ve automated that part of the pipeline now. We can use humans to create content that is perfectly well suited for them or We could automate the entire pipeline where it’s not just Us targeting the users using a I will generate content for those users using AI so the entire process Is automated right, so this video is content this video could be automated Who knows if I’m real or not right you have no idea unless you met me in real life But even then who knows maybe I was a hologram anyway content creation right so LSTM Networks are the way to do this for text, okay, so If you search LSTM Network Siraj you’ll find a great video on me explaining how they work in depth But I’ll give you a high-level overview right now so Recurrent networks are really good at predicting sequences of of text right so normal feed-forward networks, right? Normal feed-forward networks are not about predicting sequences They’re about predicting what an output would be for a given input it learns the mapping But when it comes to a sequence what happened before? Matters to what happens now what the words that you had previously like I like recording videos About AI because I love you know maybe it’s tensorflow But predict what that word is you got to know about the word AI you got to know about the word video You can’t just know you know Use the previous word you got to use the whole sequence right so what we’re current at works, too Is that every time step, It’s not just the next data point. That’s fed into the network. It’s also the previous hidden layer That’s learned over time. That’s fed into the time step and so at every time step Not just a new data point, but the previous hidden layer That was learned is fed into the network so it’s learning not just the next data point But it’s learning based on what it already learned before if that makes sense and that’s why it’s called a recurrent Network Because there is this recurrence or feedback loop. That’s happening and what’s there’s a problem though in that for recurrent networks if the sequence is Too long then there’s gonna be a problem called the vanishing gradient problem So during optimization back propagation we use the gradient Which is the difference between the real output and the predicted output we use the gradient to then update all of those layers beforehand? but what happens in recurrent networks is that the gradient gets smaller and smaller and smaller the further back we go in the network and So how do we preserve that gradient so all the layers are updated accordingly? Well, we need to trap that gradient somehow into what are called long short-term memory cell, cells that consist of gates values and these gates Trap the gradients in such a way that the vanishing gradient goes away And this allows a network to remember very very very long term sequences of data like an entire essay right so they lets us then write an entire essay or article and So you might be thinking how do I build this very complex thing and the answer is Keras, Keras is a machine learning library, Built on top of Tensorflow that lets you build very complex Deep neural networks in just a few lines of code and AI marketers can use this to automatically generate Content best suited for a particular subset of their audience so the idea is that if you have images or video Then you want to use generative adversarial networks that generates content if you want to generate audio you use wavenet And if you wanted used if you want to generate text, you use LSTM current networks like I’m talking about here and remember. I have videos for all of these models Just search my name and the model So here’s a very simple example of us using Keras in Under a hundred lines of code to generate an essay in the style of Neitzche So the text is Neitzche writing and then what it does is it takes that input data. It’s formats that data It feeds it into a model built in Keras where every line of code Corresponds to a single layer in the network, so it’s very readable code, and it’s only three layers long We optimize it using rmsprop Which is a type of gradient descent search which activation function should I use Siraj on Youtube to find a great video on all the differences between all of the different activation functions out there You know I also have a video on which optimization function should you use as well? but anyway once we do that we minimize it using a loss function and That’s it and then it what it’s going to do is it’s going to predict every word that that neech a would have said based on what it’s learned in the past and So we can use this for the entire pipeline whether we’re targeting users And then once we’ve targeted them generating content for them and we can do this for the entire marketing pipeline there’s a huge huge space for startups to come into this space and Create services for big brands for consumers to help them optimize to save time to save money to save resources Using the latest technologies and look even though I said that there are some startups out there that do this currently There’s a giant massive opportunity for new players in this space, and there’s a huge need for it as well So I hope you found this video useful Please subscribe for more programming videos and for now I’ve got a B nai so thanks for watching

, , , , , , , , , , , ,

Post navigation

76 thoughts on “AI in Marketing

  1. Hi siraj loved your content every time I am just going to do some digital marketing campaign and sell some stuff but I am going to be a computer science student in the coming months what would recommend me to learn ai and start digital marketing campaign or start digital marketing campaign

  2. hi siraj wanted to know how can we do freelancing or how can upcomming student makes money out of machine learning if he dosent want to be a part of any company
    how can we approach to the company to work remotely on the contract basis

  3. what are your views on data science? is it going to be automated or another business like web development, wherein coming years everyone will able to do it?

  4. Does anyone have any idea how Siraj shoot his videos to show both him and as well as computer screen to show what he is coding ?
    I also want to contribute my knowledge through videos with somewhere the same way in which Siraj is doing .
    He is inspiration.

  5. Hey Siraj and AI Wizards, do you guys think fractional derivatives might help address the vanishing gradient problem? https://www.sciencedirect.com/science/article/pii/S0893608017300369

  6. Sir I'm just 14 yrs old boy and i run a YouTube channel for programing and developing games and software. But I m struggling to get views and watch pls help me sir

    This is my channel pls do something
    AI with Siddhartha

  7. I'm a web & app developer, recently I wanted to get my hands dirty with ML, DL and AI. So I've been exploring AI recently and it's been a year now.
    I've been following your every single video since half a year now, and the more I watch, the more I'm attracted towards it.
    Thank you for your amazing dedication and willingness to teach the world.
    Hello siraj
    It's the world. 😊😊❤️❤️❤️

  8. Haha you have a video on everything AI related. Maybe just put a link in the video, so you don't have to explain how to find it every time.

    Love this series btw.

  9. Hey Siraj! You a very best blogger on youtube for me!:)) I want to wish you luck in your hard work, continue in the same spirit… And yours: "Hello world, it's Siraj"…. oh dude, this very funny!)))

  10. I love this. Thank you. Here's some data in exchange for the information. For some reason my biological neural network relates with you more when you're uncensored. The logic is that we're monkeys on a rock in the middle of nowhere. Why censor yourself? It, for some reason, shows to me that when you hesitate to use a curse word, you're trying to please someone. But we all curse. So what's the point lmao tl;dr Just fucking say it lmao

  11. The code on github is different from that of your video. Would be nice to have the code that does the content creation you are displaying on your video.

  12. Please make video which explains in what squance we should your video to understand whole things

  13. This is probably off topic but, Siraj, you should check out Holo: Take back the internet on Indiegogo. Its quite interesting

  14. Siraj, where is the humor in your clips. I loved your funny inserts and jokes. Its boring now. Still interesting…but :))
    And you sound so serious too!

  15. I adapted the code to give it a try with Romanian language, but the script is not coherent.
    How to improve coherence for Romanian language or other Latin language?

    The code and generated script is here:
    https://github.com/itsergiu/AI-for-script-generating-in-Romanian-based-on-novel-of-Ion-Creanga

  16. I wrote my first blog post on AI and the future of marketing. Check it out.
    http://cameronakers.com/wp-admin/post.php?post=164&action=edit

  17. I like this guy so much. Perhaps the Forth community can learn from him how to bring a topic into the mainstream? (Forth is a stackbased language, invented by Chuck Moore and is great for programming neural networks)

  18. I would have liked to have actually seen the results of the Nietsche content at the end of the video. I almost guarantee it would have been gibberish. None the less. What is the quickest way I can try this out or pay for a service that already does this?

  19. In fact, I have tried ai-write with a keyword from one of my clients, and the result is not as good as I expected, the funny thing is, they include some sentences from my client's website directly, with their brand name & service descriptions, lol!

  20. siraj i believe is younger than me but … i just wish he mentors me .i just wish if i could speak to him once .
    siraj buddy you rock .!

  21. Humans buying into their own replacement. Devaluing themselves in the process. Priceless. All the Sci-Fi movies people watched yet never learned a damn thing. Instead continue to create their own downfall. Then in real life will sit back scratching their heads asking themselves what went wrong. 😑

  22. Good job on this topic, Siraj. Artificial intelligence is a great instrument that can work wonders for your company.

  23. Engati has recently launched its own Bot Marketplace which gives you a headstart in building chatbots. It covers every industry and every use-case that anyone can ever think of and provides you with pre-built chatbot templates. Take a look – http://s.engati.com/bk8

  24. Engati has recently launched its own Bot Marketplace which gives you a headstart in building chatbots. It covers every industry and every use-case that anyone can ever think of and provides you with pre-built chatbot templates. Take a look – http://s.engati.com/bk8

Leave a Reply

Your email address will not be published. Required fields are marked *