Advancements to Machine Learning are changing the game for busy marketers, with automation possibilities from personalised messaging and content creation to social listening and predictive analysis available.
6. What is Machine Learning?
What We’ll Cover
Automation Possibilities
Powering Machine Learning
with Python
@rvtheverett@DeepCrawl(there may also be a few dogs)
8. MACHINE LEARNING
@rvtheverett@DeepCrawl
“Machine learning is an application of artificial
intelligence (AI) that provides systems the ability
to automatically learn and improve from
experience without being explicitly programmed.”
https://www.expertsystem.com/machine-learning-definition/
11. REAL WORLD MACHINE LEARNING EXAMPLES
@rvtheverett@DeepCrawl
RankBrain NLP
Computer
Vision
Keyword
Stuffing
12. REAL WORLD MACHINE LEARNING EXAMPLES
@rvtheverett@DeepCrawl
Twitter Curated Timelines
13. REAL WORLD MACHINE LEARNING EXAMPLES
@rvtheverett@DeepCrawlhttps://www.salesforce.com/uk/products/einstein/overview/
Salesforce Einstein
14. REAL WORLD MACHINE LEARNING EXAMPLES
@rvtheverett@DeepCrawlhttps://ipullrank.com/machine-learning-guide/how-to-set-up-a-chatbot/
Facebook Chatbots
15. REAL WORLD MACHINE LEARNING EXAMPLES
@rvtheverett@DeepCrawlhttps://medium.com/netflix-techblog/artwork-personalization-c589f074ad76
Personalised Recommendations
19. MACHINE LEARNING SIMPLIFIED
@rvtheverett@DeepCrawl
- Ethem Alpaydin
Machine learning will help us make sense
of an increasingly complex world. Already
we are exposed to more data than what our
sensors can cope with or our brains can
process.
21. WHY SHOULD WE CARE?
@rvtheverett@DeepCrawl
Machine Learning is becoming more accessible and
will free us up to work on higher level strategy.
Allowing us to spend time finding the solution not the
problem.
- Britney Muller
22. WHY SHOULD WE CARE?
@rvtheverett@DeepCrawl
Spend 5 hours a week using excel
Thats 20 hours a month
Over 200 hours a year
(35 hours in dog time)
(140 hours in dog time)
(1400 hours in dog time)
23. WHY SHOULD WE CARE?
@rvtheverett@DeepCrawl
Average salary for Digital
Marketing Executive in Milton
Keynes: £25,000
Average £12 per hour
£2,400 you could save
24. WHY SHOULD WE CARE?
@rvtheverett@DeepCrawl
Imagine what we could
achieve if we spent
this time (and money)
on other important
tasks
25. MARKETING POSSIBILITIES WITH MACHINE LEARNING
@rvtheverett@DeepCrawl
Marketing
Possibilities with
Machine Learning
Personalised
Marketing
Social Media
Automation Content Creation
Engage
Customers
Predictive Analysis Social Listening
26. SEO POSSIBILITIES WITH MACHINE LEARNING
@rvtheverett@DeepCrawl
SEO Possibilities with
Machine Learning
Evaluating
Content Quality
Log File
Analysis
Automating Meta
Descriptions &
Title Tags
Image
Optimisation
User Engagement
Insights
Internal Linking
Analysis
27. MACHINE LEARNING TOOLS
@rvtheverett@DeepCrawl
Google’s NLP Model
Natural Language uses machine learning to reveal the structure and meaning of text.
Analyses text to understand the sentiment, as well as extract key information.
https://cloud.google.com/natural-language/
35. WHAT IS PYTHON?
Code written in the
terminal
@rvtheverett@DeepCrawl
Results generated
Open-source interactive programming
language
Interpreted line by line
38. COMPANIES USING PYTHON
"Python has been an important part of Google
since the beginning, and remains so as the
system grows and evolves. Today dozens of
Google engineers use Python, and we're
looking for more people with skills in this
language."
@rvtheverett@DeepCrawl
39. COMPANIES USING PYTHON
"Python is fast enough for our site and
allows us to produce maintainable
features in record times, with a minimum
of developers"
@rvtheverett@DeepCrawl
40. WHY SHOULD WE CARE?
@rvtheverett@DeepCrawl
Data extraction and analysis
to solve complex problems
Future-proofing your job
Efficiency and time-saving
Automating repetitive tasks
https://www.ranksense.com/empowering-a-new-generation-of-seos-with-python/
41. @rvtheverett@DeepCrawl
WHY IS PYTHON GROWING IN POPULARITY?
Make data driven decisions
Allowing us to focus on other
important optimisation efforts
Confidence in recommendations
Provide concrete insights
Better understand data
43. CRAWL404
@rvtheverett@DeepCrawl
Once you specify the sitemap the
script will;
Read the sitemap.xml file
Check the response code of each
link
Export all 404 error URLs to a text
file
Github Link
46. OPTIMISE IMAGES WITH PILLOW
@rvtheverett@DeepCrawl
optimize-images
filename.jpg
Optimise a single image
optimize-images ./
Optimise a folder with
multiple images
Github Link
48. OPTIMISE IMAGES WITH PILLOW
@rvtheverett@DeepCrawl
Average Time Taken
Download and install script: 20 minutes
Optimise 1 image: 2 minutes
Total: 22 minutes
54. @rvtheverett@DeepCrawl
KEEP UP WITH YOUR COMPETITORS
- Gerry Brown, July 2017
By 2020, real-time personalised advertising
across digital platforms and optimised
message targeting accuracy, context and
precision will accelerate
55. KEY TAKEAWAYS
@rvtheverett@DeepCrawl
Machine learning is becoming more
accessible, freeing up valuable time for
higher level work
Automation with machine learning provides
the ability to personalise messages, optimise
campaigns and understand complex
problems.
Understanding large sets of data allows
more data driven decisions to be made and
implemented.