DATA Pill #005 - For the brainiacs : ML, Data Science and Feature Stores cheat sheets

Hi, everyone

Today we return nostalgically to our student days...

when one good cheat sheet could save you from a failed exam.

Now, we may have grown up, but a good cheat sheet is still not bad ;)

And it can be very useful.

After all, we like simple things that present complicated topics…

Today, helpful cheat sheets for you.

ARTICLES?

Machine Learning Cheat Sheet | 5 min read | Machine Learning | DataCamp Blog

A handy guide describing the most widely used machine learning models, their advantages, disadvantages, and some key use-cases.

Because we all love cheat sheets, I want to show you one more. It’s a bit older, but still…

?

Data Science Cheat Sheet for Business Leaders | 7 min read | Data Science | DataCamp Blog

The basics of how data science can help businesses, including building a data science team and the common steps in the data science workflow.

4 Feature Stores - explained and compared | 5 min read | ML &MLOps | ?? Jakub Jurczak | GetInData Blog?

4 popular Feature Stores comparison: Vertex AI Feature Store, FEAST, AWS SageMaker Feature Store and Databricks Feature Store on one cheat sheet.?

The Future of the Modern Data Stack in 2022 | 13 min read | Data Science | Prukalpa | Towards Data Science Blog?

Maybe not the newest article, but definitely one of the hottest.

The 6 big ideas you should know from 2021 - presented, analyzed and sprinkled with a prediction of the future.

1. Data Mesh - “I think we’ll see a ton of platforms rebrand and offer their services as the 'ultimate data mesh platform'. The thing is, data mesh isn’t a platform or a service that you can buy off the shelf. It’s a design concept with some wonderful concepts like distributed ownership, domain-based design, data discoverability and data product shipping standards — all of which are worth trying to operationalize in your organization.”
2. Metrics Layer?
3. Reverse ETL
4. Active metadata & Third-Gen Data Catalogs
5. Data Teams and Product Teams
6. Data Observability?

{ MORE LINKS }

?DATA BIZ & MANAGEMENT

The basics of how data science can help businesses, including building a data science team and the common steps in the data science workflow | 10 min read | Product Management | Olga Dudzik | allegro Tech?

On average, 10-20% of an IT budget is ultimately consumed by tech debt management and most CIOs interviewed consider the problem significantly increasing over past years, especially in enterprise-sized companies.

?A juicy and very specific article on how to work with technology debt, how and who to convince of the need to work on debt and how to do value mapping and roadmapping of technological debt.?

?

How to Deliver a Customer-Centric Banking and Insurance Experience with Data | 12 min read | Culture & Methods | Rinesh Patel & Jonathan Beaulier | Snowflake Blog

“Nearly 70% of consumers say they’d like their banking experience to be similar to the experiences they have with Netflix, Amazon, and other tech companies when it comes to offering personalized recommendations.”

However,? the problem is that this industry is subject to much more regulation. So how do you provide the deepest possible analytics and data security in the cloud for the financial sector? Search for the answer in this article.?

{ MORE LINKS }

?TUTORIALS?

Building a Machine Learning Pipeline With DBT | 15 min read | dbt | Joselito Balleta | MLOps.community?

Setting up a proper data pipeline that performs feature engineering, trains and makes predictions on our data can get pretty complicated.? Yet it doesn’t have to be. Check out this guide.?

?

PODCAST

Orchestrating Machine Learning Applications | 47 min |? The Data Exchange

• What is Flyte??
• Who uses Flyte?
• Multi-modal models
• Roadmap for Flyte and Union AI

{ MORE LINKS }

See You tomorrow!

Adam Kawa from GetInData