Recent content by Kevin Lee

Be careful though. I bought SPX historical intra day data from them and realized that they are missing the corresponding SPX price and some greeks before 2014. It's not a bug but they confirmed they don't have the data.

Because candidates have to take a comprehension and math test. The first one is easy. The math test includes multivariable calculus differential equations, probability and statistics, and linear algebra. They assume undergraduate level competency. It wasn’t trivial for me because I’ve forgotten...

Vladimir and I are working on a project to build an AI agent for options trading using reinforcement learning. Will loop you in if you’re interested. Already sent you private message about this.

For Python, I learned by doing and googling. If you prefer more structured courses, I strongly recommend courses in Udacity or Coursera. Lots of free Python classes. But personally, I suggest paid courses because that forces you to work on the projects. For ML and AI, I took several Nanodegree...

Regardless of one's view of artificial intelligence, one thing is irrefutable - the rise of data is already impacting every profession and our lives. Today, traditional business like banking, retail, manufacturing, logistics etc... have already turned into data driven businesses. Companies that...

Ha ha ... it looks creepy because it’s 90% human like. When a robot is only 50% human like, it won’t look creepy. It’ll just be like a toy but when it gets to 90%, it’ll becomes creepy because suddenly we start associating it as human. Whether we like it or not, robots like this will be...

For a light-hearted view of artificial intelligence..... progress in human-like robots has been staggering in recent years. Though clearly still some ways to go but it's phenomenal what has already been achieved

This is an example from a blog post on how to use neural network to predict volatility. I'm seeing more and more people attempting to use machine learning on volatility and markets as a whole. It's an interesting trend...

Mispricing, if they exist, can be found using traditional non-learning data analysis techniques. This scenario may play out in the future but that's probably many years away. Although AI has done seemingly incredible stuff, the technology is still very rudimentary. In the foreseeable future...

I'm sharing this for those who are interested in the subject. https://deepmind.com/blog/alphago-zero-learning-scratch/ I'm sure many of us are familiar with AlphaGo, the AI program by DeepMind owned by Google, that managed to beat the best human Go players, a feat unimaginable just couple...

Since I did the video, OV has already added "Mid Price" as one of the download items. Try that. Then compare the downloaded mid price of the individual option with what you see on OV. If there is a difference, then it's a bug. You should report that to OV.

Sorry not sure I understand your question. What are the two sources you're comparing? OV backtrader data vs what?

Oh I see what you are asking now. If you started with a 2 tranche M3 and exited 1 tranche, I would treat the remainder as 1 tranche and decide on adjustments based on 1 tranche greeks.

Hi Sergei, You'll first need to work out the profit targets and exit timing as part of your trade plan and ensure that plan is properly back tested. Although we can be trading the same M3, but different M3 trade plan will call for a different decision on adjustments as well as profit taking...

Glad that you found a solution to the issue. I started to look at my options position differently after I listened to Elon Musk talk about the concept of First Principle Thinking. Here's a good video on that subject and another article...