message match in advertisement
message match in advertisement
message match in advertisement

Personalization

Mar 7, 2024

Message Match: Identify and Overcome Common Advertisement Pitfalls

ankur goyal

Ankur Goyal

5 mins to read

Introduction

Mobile games can be a delightful escape, offering stress relief and entertainment. Or, in my case, it is a good way to add stress to my life! I'm just kidding! It's a great way to stimulate my brain.


One of my favourites is a color puzzle game where you arrange colored liquids in bottles until each bottle holds a single color. It's simple and enjoyable, except for those levels that leave me stumped. Maybe that's part of the strategy to keep me hooked. We can discuss the ethics of difficulty manipulation later.


Let me draw your attention to the advertisements you get for other games. Their trailers are so convincing you won't be able to resist them for long. The moment you download it, 99/100 times it's a simple matching game with nothing but just basic icons for graphics and not even one character as in the trailer or the story line which you were promised. Their trailers set the bar so high and then end up just not even making the passing marks.


Even if I was really into the game and wanted to give it a shot, it turned out to be more of a let-down than anything else. We've all been there, right? (I know you can feel the emotions right now) You see something advertised, and it seems amazing, but then it doesn't live up to the hype. Just like with those games I tried and ended up uninstalling.


If the ads don't match the actual product, they might catch the user's eye for a bit, but they're not going to keep them hooked.

Which is why Message Match is important

Message match is as simple as it sounds, matching the advertisement with the landing page. For example, if your ad says "Free Trial of XYZ Software," your landing page headline should also say "Free Trial of XYZ Software" or something very similar. Message match is important because it increases conversions by reassuring the visitor that they have come to the right place and that you can deliver on the promise of the ad. A strong message match can also reduce bounce rates and improve quality scores for PPC campaigns.


Good Message Match is when the headline, text, or offer of your ad matches the content of your landing page. This can increase conversions by reassuring the visitor that they have come to the right place and that you can deliver on the promise of the ad. An advertisement that promises a free consultation for online dating and a landing page that also offers a free consultation with a catchy headline and a clear call-to-action is a good message match because the visitor gets exactly what they expected from the ad! They are more likely to sign up for the consultation. 


A message mismatch would be to have a landing page that does not mention a free consultation or that has a different offer or headline. This would confuse or disappoint the visitors, and they might leave without converting.


Bad Message Match is when the headline, text, or offer of your ad does not match the content of your landing page. This can confuse or disappoint the visitors who click on your ad and make them leave without converting. Suppose an ad promises a free trial of software, but the landing page does not mention anything about a free trial. Instead, it asks the visitor to fill out a form to get a demo. 


This is a bad message match because the visitor expects to get a free trial, not a demo, and they might feel misled or frustrated by the landing page. A good message match would be to have a landing page that clearly offers a free trial and explains how to get started. This would increase the chances of the visitor signing up and becoming a customer!

Real life examples of message-match success

I'll share real-life examples of successful companies. They've boosted their revenue by using message match ad campaigns and dynamic landing pages in their marketing strategies.


  1. Airbnb: Planning a vacation can feel like a task, getting ready for it is another chore, and even when you finally reach your destination, it can still feel like work trying to cover all the tourist spots. But regardless of how you choose to enjoy your vacation, finding good accommodation is always a priority. Airbnb, a company that excels in this area, used a clever strategy to enhance its marketing efforts. They employed message matches in their ads, tailoring them to specific travel desires and paired them with dynamic landing pages. For instance, ads aimed at users searching for "romantic getaways" directed them to pages featuring cozy cabins and luxurious resorts rather than family-friendly apartments. This approach led to a remarkable 20% increase in booking conversions.


     

  2. Spotify: Spotify, a well-known company in the music streaming industry, has a knack for marketing. While my Spotify Wrapped experience might have been a bit chaotic, I still appreciate their marketing strategy. They really know how to do it right. One of their brilliant tactics involves focused message matching on specific music genres and artists. For example, if a user clicks on an ad for a particular artist, they're directed to personalized playlists or artist pages. This approach resulted in a significant 30% increase in subscription signups.



  3. Nike: As someone who loves both running and casual wear, I've always been impressed by how Nike tailors their ads to suit different preferences. Whether I'm hunting for performance shoes to enhance my runs or seeking stylish casual wear for everyday use, Nike's ads always seem to hit the mark. But how do they manage to do that? It's all thanks to their use of message-matched advertisements paired with dynamic landing pages. 



  4. Duolingo: As someone deeply passionate about learning new languages, I've always been driven by a variety of motivations. When I encounter advertisements for Duolingo, I'm immediately captivated by how well they grasp and cater to these motivations. Whether it's their quirky notification messages or the design of their app, Duolingo consistently impresses. One aspect that stands out to many of their customers is how closely the app aligns with its advertisements, which undoubtedly motivates them to download the app. Duolingo's approach involves tailoring ad messages to match different language learning motivations. For instance, ads highlighting career advancement led users to job-focused content, while those appealing to cultural immersion directed them to travel-related resources. This strategic alignment resulted in a remarkable 25% increase in app downloads.

How does message match work?

When I see an ad, it's specifically tailored to my interests and preferences. If I click on the ad, I'm immediately taken to a dynamic landing page showcasing the exact product I am interested in.


This seamless transition eliminates all the hassle of searching and browsing through endless options. It's like a shortcut straight to the product I want to buy. It's no wonder customers find this approach so convenient.


They can simply add the product to their cart and make the purchase without any unnecessary steps. This personalized shopping experience has elevated customer experience, which was reflected by a 15% increase in average order value.

Conclusion

These examples prove that ensuring a message match between advertisements and landing pages is crucial for a successful marketing campaign. We've all experienced the disappointment of clicking on an enticing ad only to find that the landing page doesn't deliver what was promised.


This disconnect not only frustrates users but also leads to missed conversion opportunities. By aligning ad messages with landing page content, businesses can create a seamless and trustworthy experience for their audience. When users see consistent messaging from the ad to the landing page, they feel confident that they're in the right place to find what they're looking for. This builds trust and increases the likelihood of conversions.


So, if you want to improve your marketing performance and maximize conversions, prioritize message matches in your campaigns. Remember, consistency is key to earning the trust of your audience and driving results.


Now, if you are convinced to take a second look at your ads and make them better by ensuring message match along with dynamic landing pages but are unsure how or where to start, book a free demo with Fibr today. Fibr, which is an AI-powered web personalization tool, creates just the landing pages you want and need! 


Try Fibr today!

<!-----



Conversion time: 0.426 seconds.


Using this Markdown file:

1. Paste this output into your source file.
2. See the notes and action items below regarding this conversion run.
3. Check the rendered output (headings, lists, code blocks, tables) for proper
   formatting and use a linkchecker before you publish this page.

Conversion notes:

* Docs to Markdown version 1.0β35
* Thu Mar 21 2024 00:22:11 GMT-0700 (PDT)
* Source doc: PII Detection Library
* This is a partial selection. Check to make sure intra-doc links work.
----->



# PII Library 


## Problem Literature : 

According to NIST, these are what considered to be PII, sorted in the order by criticality :



* Full name
* Home address
* Email address
* Telephone number
* Social security number
* National Identification Number
* Passport number
* Driver's license number
* Credit card numbers
* Date of birth
* Log in details
* Gender
* Race
* Device IDs
* IP addresses

This is the standard list of what is identified as PII, however, the list is NOT exhaustive and subjected to change based on the internet laws of operation of a region. Also, in certain cases its a grey area. For example, a web cookie is not considered PII, however storing a customer id, makes it a PII.

Task at hand is to have a system where we feed data and the system reports back the PII information found in that data. There are already some systems available which does pretty much the same. Some options that were considered for are : 



* [https://pypi.org/project/piicatcher/](https://pypi.org/project/piicatcher/)
* [https://github.com/solvvy/redact-pii](https://github.com/solvvy/redact-pii)
* [https://pypi.org/project/piianalyzer/0.1.0/#description](https://pypi.org/project/piianalyzer/0.1.0/#description)

The base idea behind all of these modules is 1:1 regex matching for detection and redaction. Although, that's precisely the way such a problem should be solved, however, they are not full proof and does not guarantee 100 % detection. The goal here is to understand how to increase the detection efficiency for this technique. In order to understand the complexity of the detection, we will iterate through the list of PII data and discuss detection techniques, for each one of them in the increasing order of detection difficulty.



1. **IP addresses,Device IDs, Email address, Passport number, Social Security number, Gender, Race**: They are straight forward regex detection, as their formats are standard across all platforms, devices and region. 1 to 1 regex matching.
2. **Credit card numbers ,Telephone number, National Identification Number, Driver's license number, Dates, Addresses** : These are particularly difficult to detect with just one regex on its own, as incase of National IDs, every nation has their own format. 
3. **Full name (Entity Names), Login Details :** These are the hardest to detect. Most of the libraries stated above is either doing static lookups from standard name databases or using contextual NLP for detecting entity names.

Based on this, we can see there are clearly three categories in which PII can be split based on their detection mechanisms, baring the grey areas of dealing with authentication tokens and web cookies with customer id. 


## Proposed Solution : 

The solution is divided into two phases : 


## Phase 1 : (token extractor)



* Every stream is matched against list of regexes of each category. Difference is, instead of matching 1-1 regex for each category, it matches to a bunch of regexes for 1 category and returns a probability score for each of the identified tokens. The probability score for a token is determined  by number of regex where this token was returned vs total number of regexes. For example : 

**Sample Text **contains same phone number in the following formats (world wide standards) : 

E164 format: +918197800510

Original format: 81978 00510

National format: 081978 00510

International format: +91 81978 00510

Out-of-country format from US: 011 91 81978 00510

Out-of-country format from Switzerland: 00 91 81978 00510

**Regex 1** : ^(\(?\+?[0-9]*\)?)?[0-9_\- \(\)]*$/igm

Validates all to be correct.

**Regex 2** : (\d?[^\s\w]*(?:\(?\d{3}\)?\W*)?\d{3}\W*\d{4}) -> Regex from CommonRegex lib.

Validates 2 correctly.

 \
Determining the probability for the individual tokens **_(Number of regexes matched / Total  number of regexes)_** : 



* +918197800510  =  1
*  81978 00510 = 1
*  081978 00510  = 0.5
* +91 81978 00510 =  0.5
* 011 91 81978 00510 = 0.5
* 00 91 81978 0051 = 0.5

This way, the system will be able to determine any and all supported forms of phone number detections. This is a quick preview of the potential PII detected. Phase 2 is what will confirm the determination. The probability score is needed for phase 2 evaluation. Similar evaluations are to be in place for all the categories of the PII data. In case certain detection fails, for any category of data, it's all about finding the right regexes to be added to the list, which validates detects the information.


## Phase 2: (token assertion)

Phase 2 incorporates spacy rule based matching model mechanism [https://spacy.io/usage/rule-based-matching](https://spacy.io/usage/rule-based-matching).  Here, the tokens / analysis received from phase 1, becomes the labelled training data which will be used for training our model and our test data, is the original stream passed in the library. The NLP model will serve as an assertion mechanism for the data passed from phase 2, till the point where test data results in equivalent or better analysis than the regex matches. Also, this is the only mechanism via which named entities can be detected. 

Reasons to use the rule based matching model is that the model will be trained faster and better for labelled data. Given that the training data (tokens from phase 1) are already noise free, model shows a better response than training via unclean data. Furthermore, passing the unclean or actual text as test data, provides assertion instantly hence helping the model to be updated automatically without any intervention. 


### Typical Response example from PII Analyzer Library : 

[https://jsoneditoronline.org/?id=d0373eeba1294f5f88ce34b9ac2a8258](https://jsoneditoronline.org/?id=d0373eeba1294f5f88ce34b9ac2a8258)

ankur goyal

Ankur Goyal

Ankur Goyal, a visionary entrepreneur, is the driving force behind Fibr, a groundbreaking AI co-pilot for websites. With a dual degree from Stanford University and IIT Delhi, Ankur brings a unique blend of technical prowess and business acumen to the table. This isn't his first rodeo; Ankur is a seasoned entrepreneur with a keen understanding of consumer behavior, web dynamics, and AI. Through Fibr, he aims to revolutionize the way websites engage with users, making digital interactions smarter and more intuitive.