Most of my ML model prototypes never reached production 😵‍💫

Until I changed my mindset 🧠↓↓↓ 🔬 Model-first mindset

A model-first mindset is what Kaggle competitions and most online courses are about.

Your ONLY focus is to build the best possible mapping between a set of input features, and a target metric

And in real-world ML this is often not the best approach...

How do you build
> 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 ML systems ⚡
> at 𝘀𝗰𝗮𝗹𝗲 🎛️
> 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗯𝘂𝗿𝗻𝗶𝗻𝗴 𝗰𝗮𝘀𝗵 💸?

🧵↓ 𝗧𝗵𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺 🤔

Let’s say you work as an ML engineer at a fintech startup, whose flagship product is a mobile app for online payments.

A critical problem you need to tackle from day 0 is the automatic detection of fraudulent transactions.

ML Project Idea 💡

Let's predict taxi demand in NYC in the next 60 minutes 🚕↓ Business problem 💼

Let's create a predictive model to forecast the number of taxi rides that will happen in Manhattan (New York City)

- in the next hour
- for each taxi zone (e.g. Zone 113 "Lower Manhattan)

Let's do it in 6 steps ↓

ML Project Idea 💡

Let's predict flight delays 🛬 ↓ Here is a full example, with source code, to learn how to build a complete ML app that predicts flight delays for Stockholm Arlanda airport.

Clone the code, modify it, and deploy it!
github.com/SebastianoMene…

Let's build an LLM agent in Python, step-by-step ↓🧵 Why agents 🤖❓

Because Large Language Models alone are not enough to accurately answer complex tasks that require

-> External information that was not present in the training dataset used to fit the LLM paramaters
or
-> Many reasoning steps

ML Project Idea 💡

Let's predict flight delays 🛬 ↓ Here is a full example, with source code, to learn how to build a complete ML app that predicts flight delays for Stockholm Arlanda airport.

Clone the code, modify it, and deploy it!
github.com/SebastianoMene…

ML Project Idea 💡

Let's predict air quality ↓ Here is a full example, with source code, to learn how to build a complete ML app that predicts air quality in different European cities.

Clone the code, modify it, and deploy it!
github.com/logicalclocks/…

Wanna learn time-series forecasting? 📈

No more reading blog posts.
It is time to forecast for real 😎

Here is a project you can build 👩‍💻🧑🏽‍💻↓ Business problem 💼

Let's create a predictive model to forecast the number of taxi rides that will happen in Manhattan (New York City)

- per hour (e.g. tomorrow between 5 PM and 6 PM), and
- per zone (e.g. Zone 113 "Lower Manhattan)

in the following 3 days.

Wanna become an NLP engineer?

Stop taking online courses.
Build something instead 🏗️

Here is a project you can build 👩🏽‍💻👨‍💻↓↓↓ Reading blog posts about multi-billion-parameter Language Models is very cool.

However, building real-world NLP products from these models is where the real business value is. And this is what companies look for in the job market.

So, here is a PRO project you can build ↓

Tired of training lots of Machine Learning models, and not getting better results? 😵‍💫

This is how you solve this 🧠↓ A Machine Learning model is the output of a 3-step workflow where you:

1 → Fetch raw data, for example from an external database.

2 → Process the data into a tabular format, so you have N features and 1 target.

3 → Train ML models (e.g. XGBoost) and tune hyper-parameters.

The one skill every professional data scientist must have? 🤔

Don't look for it in online courses, it's not there.

Read the thread below and find out ↓↓↓ In the real world, data science projects start from a business problem.

They are born to move a key business metric (KPI):

And you, as a data scientist, need to

1 → Understand the business problem

2 → Transform the business problem into a data science problem

3 → Solve it

Let's build an LLM agent in Python, step-by-step ↓🧵 Why agents 🤖❓

Because Large Language Models alone are not enough to accurately answer complex tasks that require

-> External information that was not present in the training dataset used to fit the LLM paramaters
or
-> Many reasoning steps

How do you test your ML model before deploying it?

3 strategies to help you 🧠 ↓ A better offline metric does NOT mean a better model, because

→ An offline metric (e.g test ROC) is *just* a proxy for the actual business metric you care about (e.g money lost in fraudulent transactions)

→ The ML model is just a small bit of the whole ML system in production

3 years ago I struggled to build ML products.

Then I discovered this ↓ Unless you are a researcher in academia, and your goal is to publish a paper, you cannot just focus on the ML model you wanna train.

You need to think further down the line and think of the business problem you are trying to solve.

This is the "product-first" mindset.

Let's build an AI Coding assistant with Llama3 ↓🧵🦙 Step 1. Download llama3 with Ollama 🦙

Ollama is an open-source tool to run Large Language Models locally, that you can download for free from here.

ollama.com/download

Let's build an AI Coding assistant with Llama3 ↓🧵🦙 Step 1. Download llama3 with Ollama 🦙

Ollama is an open-source tool to run Large Language Models locally, that you can download for free from here.

ollama.com/download

Wanna learn enough git to be a data scientist?

A hands-on tutorial in 10 steps 👩🏽‍💻👨‍💻↓↓↓ #1 Create your project folder and cd into it

XGBoost is one of the most effective algorithms for time-series prediction.

But, you need to prepare your data carefully.

These are the steps to transform raw data into supervised ML data for time-series prediction ↓ Example

Imagine you work at a ride-sharing app company in NYC as an ML engineer.

You want to help the operations team allocate the fleet of drivers optimally each hour of the day.

The end goal is to maximize revenue

ML Project Idea 💡

Let's find your Twin Celebrity 🔎👸 ↓ Here is a full example, with source code, to learn how to build a complete ML app that finds your Twin Celebrity

Clone the code, modify it, and deploy it!
github.com/SaladSlayer00/…

Training an ML model inside a Jupyter notebook is something every data scientist knows 🏋️

But do you know how to create a real-world ML service that makes a difference for the company you work for? 📈

If the answer is NO, this thread is for you 🤗🧵↓ So, what is the difference between model training and ML service? 🤔

An ML service is a sequence of processing and storage steps that takes in raw data and outputs predictions that are used by the business to make smarter decisions.

Model training is just one of those steps.

ML Project Idea 💡

Let's predict taxi demand in NYC in the next 60 minutes 🚕↓ Business problem 💼

Let's create a predictive model to forecast the number of taxi rides that will happen in Manhattan (New York City)

- in the next hour
- for each taxi zone (e.g. Zone 113 "Lower Manhattan)

Let's do it in 6 steps ↓