Our Data Science team used a neural network model to classify invalid and valid emails. They applied a convolutional neural network (CNN) and recurrent neural network (RNN) layers to capture and remember patterns in the email address. CNNs are traditionally used in image processing, but were used here to create n-gram data of character sequences which are fed to an RNN. The RNN is able to learn the patterns of these character sequences which it uses to distinguish valid email addresses from invalid [...]
[more]
sendgrid.com 
Intelligence
The journey of how we worked alongside 35 of our brands as developed Smart Send Time. We’ll show how and why it works and why it outperforms standard personalization techniques. Key findings: Sending email at different times of the day leads to different open rates; Using historical sent/opened data to make either list wide or personalized predictions does not provide substantial lift. Why? Missing data — Most companies have never tested an afternoon or evening send time, so we can’t make any [...]
[more]
klaviyo.tech
Intelligence, Sendtime
Während der Erstellung eines Mailings klickt die E-Mail-Software eigenständig durch die hinterlegten Links und analysiert alle Landeseiten. Die bis zu 130 wichtigsten Mikrodaten werden pro Landingpage gespeichert. Klickt der Newsletter-Empfänger auf einen Link im Mailing, können ihm - Tracking Permission vorausgesetzt - diese Mikrodaten zugeordnet werden. Durch die Analyse des individuellen Klickverhaltens über einen gewissen Zeitraum verdichtet sich das Interessensprofil der Kunden immer mehr. Mit [...]
[more]
email-marketing-forum.de 
Customization, Intelligence, Tool
What are your best sellers? How about those from last year? These classic recommendations instill customer confidence. Highlight them, along with your products best known for converting first-time customers. And if your customer experience is great enough, those new shoppers may even by loyalists by February. Tory Burch does this well, with a single beautiful, eye-catching image and just a few words. Though it’s short and sweet, Tory Burch’s copy manages to creates a sense of exclusivity and [...]
[more]
sailthru.com
Gallery, Intelligence
There’s plenty of time before “the holidays,” right? Not exactly. Holiday sales are perpetually on the rise, while consumers are starting their shopping earlier and earlier. This means retailers must get a head start before the holidays, especially since the most wonderful time of the year is also the most lucrative. [...]
[more] 
sailthru.com
Event, Intelligence
Today, at Salesforce Connections, we’re excited to announce new Einstein AI enhancements to Marketing Cloud that will empower brands to increase customer engagement with relevant and timely email marketing messages–an invaluable channel for marketers. The latest State of the Connected Customer report shows that 64 percent of customers prefer email communications over other digital channels such as mobile and social media. And for every $1 a company invests in email marketing, the return is $42. [...]
[more]
salesforce.com
Intelligence, Trend
Die Verfügbarkeit detaillierter Echtzeit-Kennzahlen gehört zur DNA des Online -Marketing. Das E-Mail-Marketing bildet dabei keine Ausnahme. Geeignete Key Performance Indikatoren (KPIs) sind dabei essentielle Werkzeuge zur Bewertung, Steuerung und Optimierung der verschiedenen Online-Marketing-Kanäle. Besonders interessant sind dabei alle Kennzahlen, die das Engagement der User möglichst genau erfassen, denn Engagement ist der Schlüssel zum nachhaltigen ROI des E-Mail-Kanals. Generell sind [...]
[more]
xqueue.de
Intelligence
There’s some noise in the email industry around Google’s new draft API policy framework, and the verbal comment from some people (though not all) at Oath/Verizon Media Group that they will follow suit. The noise is for good reason. This action would be a real and unnecessary blow to email marketers everywhere. I understand what [...]
[more]
returnpath.com
Intelligence, Law
Brands use analytics to listen to what their subscribers and inbox providers are telling them. Without analytics, brands are deaf to both their cheers of happiness and their shouts of frustration. Based on our State of Email Survey of 3,000 marketers, our first-ever State of Email Analytics report takes a detailed look at the email metrics brands measure, the analytics tools they use, and the impact of the two of those on program performance. [...]
[more]
pardot.com
Intelligence, Study
“Not everything that counts can be counted, and not everything that can be counted counts.” I think this 1963 quote from William Bruce Cameron (often misattributed to Albert Einstein) touches on some of the potential pitfalls of marketing dashboards. In this era of data-driven marketing, dashboards can give marketers a false sense of security. They always appear authoritative, but the true value depends on what’s being measured. [...]
[more]
marketoonist.com
Intelligence
Einer der riesigen Vorteile von E-Mail-Marketing ist die Verfügbarkeit einer Vielzahl von spannenden Kennzahlen. Erst diese Kennzahlen machen es möglich, die Newsletter einer Erfolgskontrolle zu unterziehen und eine Verbesserung Ihrer eMailings zu erreichen. Denn was man nicht messen kann, kann man auch nicht optimieren. Doch bei der Interpretation der Kennzahlen werden immer wieder Fehler gemacht. Die häufigsten Irrtümer haben wir hier für Sie zusammengefasst – damit Sie es richtig machen! [...]
[more]
email-marketing-forum.de
Intelligence
arketers often use A/B testing as a tactical tool to compare marketing treatments in a test stage and then deploy the better-performing treatment to the remainder of the consumer population. While these tests have traditionally been analyzed using hypothesis testing, we re-frame such tactical tests as an explicit trade-off between the opportunity cost of the test (where some customers receive a sub-optimal treatment) and the potential losses associated with deploying a sub-optimal treatment to the [...]
[more]
arxiv.org
Intelligence, Test
Dieser Artikel ist der dritte Teil einer mehrteiligen Anleitungsreihe, in der Ihnen gezeigt wird, wie Sie in der Google Cloud Platform (GCP) mit TensorFlow und der Cloud Machine Learning Engine ein auf maschinellem Lernen (ML) basierendes Empfehlungssystem implementieren. In diesem Teil erfahren Sie, wie Sie das TensorFlow-Modell auf Daten aus Google Analytics 360 anwenden, um Inhaltsempfehlungen für eine Website zu erhalten. [...]
[more]
google.com
Customization, Intelligence, Webanalytics
EPiCβ - Rene's daily Email PiCks
2018 State of Email Analytics: The Metrics Brands Measure and the Impact of Third-Party Analytics [PDF]