use free machine learning apis #brightonseo
TRANSCRIPT
International Freelance SEO
International Freelance
SEO
Brand Ambassador
Majestic
Cycling & Skating
Science: Physics in
particular
http://www.cyclingacrosstheworld.com
“A computer program is said to learn from
experience E with respect to some task T
and some performance measure P, if its
performance on T, as measured by P,
improves with experience E.” -Tom Mitchell,
Carnegie Mellon University
E: 50 years of data about housing prices in
Brighton
T: Pricing prediction to sell at right price
P: the better price predictions it gives, the
better future predictions will be
The goal of ML is never to make “perfect”
guesses, because ML deals in domains where
there is no such thing. The goal is to make
guesses that are good enough to be useful.
British mathematician and professor of statistics
George E. P. Box that “all models are wrong, but
some are useful”
Document Sentiment analysis of a specific URL:
{
"status": "OK",
"url": " https://www.notprovided.eu/why-not-use-googles-wmt-data/ ",
"totalTransactions": "1",
"language": "english",
"docSentiment": [
{
"mixed": "1",
"score": "0.412838",
"type": "positive"
}
]
}
You know
what you are
looking for
What do these
datapoints have
in common?
E: 50 years of data about housing prices
in Brighton
T: Pricing prediction to sell at right price
P: the better price predictions it gives, the
better future predictions will be
No rules teached. It took Google’s AI thousands of games to detect losing was probably bad
https://www.udacity.com/course/viewer#!/c-ud120/l-2254358555/m-2374468553
Best to start with:
• https://www.coursera.org/learn/machine-learning
by Andrew Ng (Baidu, former Google Brain)
• Tom Mitchell lectures:
http://www.cs.cmu.edu/~tom/10601_fall2012/lect
ures.shtml
• https://work.caltech.edu/telecourse.html Caltech
ML course
http://pdf.th7.cn/down/files/1312/machine_learning_for_hackers.pdf
Mainly use pre trained models:
– Spam classification of user generated content
(comments & reviews)
– Content classification
– Text extraction from pages
– Data gathering
• Query classification
• Recommendation engines: internal linking
based on both e-commerce, user
behaviour and SEO metrics.
http://blog.mashape.com/list-of-50-
machine-learning-apis/
• No NLP or Machine Learning knowledge is
required.
• Lot’s of pre trained models & you can train
your own models
Machine Learning based scraping,Yeah!
https://www.notprovided.eu/7-tools-web-scraping-use-
data-journalism-creating-insightful-content/
1. Collected all hotel reviews
2. Check sentiment and main entities
3. Upload search volume and e-commerce
data per hotel
4. Update UX & internal linking accordingly
?
1. Collected all hotel reviews
2. Plotted against time
3. Extract upcoming entities and sentiments
4. Predict future search behaviour
5. Create landingpages for future targeting
How about using Machine Learning
Tip: Check both the homepage and the specific link page!
Input: a URL -> output: plain text
Input text without
HTML!
• A list of links containing
– Content language
– Content topic
– Spam probability
– Content sentiment (if wanted)
– Prioritized on language relevancy
• 10.000+ keywords? Use a ML classifier
• Check for entities like places for local
• Buying intent vs informational
PersonaCustomer
journey stagePage Type
Local
identifierTag Keyword
Leisure NL Awareness Product Yes Campingaz Campingaz Munich
Leisure NL Awareness Informational No terrasverwarmer
Leisure NL Awareness Informational No terrasverwarming
Leisure NL Awareness Informational No BBQ gasbarbecue
Leisure NL Awareness Informational No BBQ gas bbq
Leisure NL Consideration Informational No Generic gasfles
Leisure NL Retention Informational No Generic gasfles vullen
Leisure NL Retention Informational No Branded primagaz
Leisure NL Consideration Informational No Generic gasfles kopen
B2B-industrie Awareness Informational No LNG lng
Leisure NL Consideration Product No Generic gasflessen
Leisure NL Awareness Informational No Generic kookplaat gas
Energie Awareness Informational No Propaan propaan
Leisure NL Awareness Informational No Butaan butaan
"I liked the book you gave me yesterday, but
the rest of my day was terrible."
• Restructure website content based on a
set taxonomy of topics
• Extract texts from top 30 and define text
requirements (eg. Searchmetrics module)
• Purchase prediction for new queries
• Use Google Tensorflow to identify image
contents
• Crawl topic related content
• Generate automatic descriptions and paragraph
text
• Build a image library site including text, good for
SEO
https://databricks.com/blog/2016/01/25/deep-learning-with-spark-and-tensorflow.html
https://www.quora.com/Machine-Learning/How-
do-I-learn-machine-learning-1