$wi4

Trader & Investor

[Visual Studio Code @code]

Introducing new GitHub Copilot features in VS Code!

There's a LOT going on, so here's everything we have to show you...🧵

[$wi4 @DRyabich]

Once I have reverced the question and phrased it like "if I generate a bunch of random variables with some volatility-will the mean absolute return of this distribution be x?" , then he finally got the right idea.

[$wi4 @DRyabich]

I had to #interview a very bright PHD guy for a position at #Options firm. He nailed every question aside from one...

[$wi4 @DRyabich]

Most people get tricked because we are used to thoughtlessly apply STD formula

[Aurimas Griciūnas @Aurimas_Gr]

What is 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 (𝗖𝗧) in MLOps and what steps are needed to achieve it?

CT is the process of automated ML Model retraining in Production Environments on a specific trigger. Let’s look into some prerequisites for this:

1️⃣ Automation of ML Pipelines.

👉 Pipelines are orchestrated.
👉 Each pipeline step is developed independently and is able to run on different technology stacks.
👉 Pipelines are treated as a code artifact.

✅ You deploy Pipelines instead of Model Artifacts allowing Continuous Training In production.
✅ Reuse of components allows for rapid experimentation.

2️⃣ Introduction of strict Data and Model Validation steps in the ML Pipeline.

👉 Data is validated before training the Model. If inconsistencies are found - Pipeline is aborted.
👉 Model is validated after training. Only after it passes the validation is it handed over for deployment.

✅ Short circuits of the Pipeline allow for safe CT in production.

3️⃣ Introduction of ML Metadata Store.

👉 Any Metadata related to ML artifact creation is tracked here.
👉 We also track performance of the ML Model.

✅ Experiments become reproducible and comparable between each other.
✅ Model Registry could and in some cases should be treated as part of ML Metadata Store.

4️⃣ Different Pipeline triggers in production.

👉 Ad-hoc.
👉 Cron.
👉 Reactive to Metrics produced in Model Monitoring System.
👉 Arrival of New Data.

✅ This is where the Continuous Training is actually triggered.

5️⃣ Introduction of Feature Store (Optional).

👉 Avoid work duplication when defining features.
👉 Reduce risk of Training/Serving Skew.

𝗠𝘆 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀 𝗼𝗻 𝗖𝗧:

➡️ Introduction of CT is not straightforward and you should approach it iteratively. The following could be good Quarterly Goals to set:

👉 Experiment Tracking is extremely important at any level of ML Maturity and the least invasive in the process of ML Model training - I would start with ML Metadata Store introduction.
👉 Orchestration of ML Pipelines is always a good idea, there are many tools supporting this (Airflow, Kubeflow, VertexAI etc.). If you are not doing it yet - grab this next, also make the validation steps part of this goal.
👉 The need for Feature Store will wary on the types of Models you are deploying. I would only suggest prioritizing it if you have Models that perform Online predictions as it will help with avoiding Training/Serving Skew.
👉 Don’t rush with Automated retraining. Ad-hoc and on-schedule will bring you a long way.

Let me know your thoughts! 👇

--------

Follow me to upskill in #MLOps, #MachineLearning, #DataEngineering, #DataScience and overall #Data space.

Also hit 🔔to stay notified about new content.
𝗗𝗼𝗻’𝘁 𝗳𝗼𝗿𝗴𝗲𝘁 𝘁𝗼 𝗹𝗶𝗸𝗲 💙, 𝘀𝗵𝗮𝗿𝗲 𝗮𝗻𝗱 𝗰𝗼𝗺𝗺𝗲𝗻𝘁!

Join a growing community of Data Professionals by subscribing to my 𝗡𝗲𝘄𝘀𝗹𝗲𝘁𝘁𝗲𝗿.

[Stat Arb @quant_arb]

Just a few graphs that give a lot of intuition about basic strategies. 👀A picture says a million words🧩.

Peek below:

...

[Jim Fan @DrJimFan]

Wolfram Plugin launch blog: https://t.co/ofTn8J2fcr

[Stat Arb @quant_arb]

On this point, I think Euan has a lot to share + it is so expensive that I expect only practitioners can afford it.

I'd say main points from him:
- bro just use statistics
- monte carlo monte carlo monte fucking carlo (I agree)
- understand your edge and trade accordingly

[Kyle Grieve @IrrationalMrkts]

The most legendary investor of all time: Warren Buffett

In 1987, Warren wrote a letter to Berkshire shareholders covering a variety of vital long-term investing topics.

In just 16 paragraphs he put together a masterclass in business & investing.

Here's a breakdown of each one:

[Stat Arb @quant_arb]

Finished writing a full guide on pairs trading, specifically finding great portfolios. It’s a pretty comprehensive dive into the topic.

Pairs trading is an area I worked on for a while, but long enough ago that I’m happy to share my insights on it

https://t.co/86iS9JQqgA

[Turing Post (Ksenia Se) @TheTuringPost]

Machine learning is famous for its open resources.

We collected 3 free courses about ML:

▪️ Introduction to Machine Learning, @MIT
▪️ Mathematics for Computer Science, @MIT
▪️ Practical Deep Learning, @fastdotai

🧵

[Daniel Mahncke @MnkeDaniel]

2 PDF‘s of Charlie Munger that every Investor should’ve read:

- Charlie Munger‘s Harvard Speech “The Psychology of Human Misjudgment”

- “The Art of Stock Picking”

You can find both PDF’s for free on my Website:
https://t.co/TtH93zeco0

[Bytebytego @bytebytego]

Very nice illustration of the Data Pipeline by Semantix. It may provide some insights into understanding data pipelines.

Subscribe to our system design newsletter to get a Free System Design PDF (158 pages): https://t.co/st1UJgX3QR

[$wi4 @DRyabich]

https://t.co/2W9HrvtfCB

[PyQuant News 🐍 @pyquantnews]

The article provides a comprehensive guide for using the wavelet transform in machine learning with examples and code snippets.

https://t.co/PJoRou3LpB

[Andrew Lokenauth @FluentInFinance]

2) @RunWayML:

AI technology allows you to create your own video or movie just by writing an idea. Bring your ideas to life.

With RunWayML, you don't need any filmmaking or editing experience - just your imagination.

AI technology turns your vision into a video.

[Tivadar Danka @TivadarDanka]

Matrix multiplication is not easy to understand.

Even looking at the definition used to make me sweat, let alone trying to comprehend the pattern. Yet, there is a stunningly simple explanation behind it.

Let's pull back the curtain!