More HFT patterns to watch for…


Jun 21

HFT’s like to buy the low of the market. The way this game works is (1) add significant size to book just below the lows, (2) aggressively buy the market near the lows. The HFT knows that both long and short biased traders are more likely to experience cognitive biases near price lows. This will have the effect of (1) creating an impression of strong support, (2) stopping out short traders. The HFT traders knowing they create the support can meanwhile take advantage of the stop runs of small short traders to load their short positions. The HFTs can infer the price discovery process because of the changes in the order book. So, they know where the shorts predicted the market to go.

It is then trivial to pull their support from the market. They know that the impression of strong support is more likely to entice technical traders to buy the lows. Unfortunately for such technical traders, they didn’t realize the HFT were simply loading their short position. And, now the technical traders buying the strong lows will provide the liquidity for the shorts to cover lower at next stop run.

Large traders may also signal intention to take shorts by adding buy limit size to the book. As contrary as it might seem, imagine if a large trader wants to get short from 38.50/75. Imagine the market is 35.50.  They will support the book at the lows and aggressively buy the market. They will put big size on 38.50/75 to entice the market to trade up to that level. It is there that perhaps they anticipate a stop run to occur. The stop run they need to get short.

While this is speculative narrative, with probably several inaccuracies, it is possible to see many sorts of order book and order flow patterns if one has an excellent market reading tool like my AlphaReveal.


About the Author

The author is passionate about markets. He has developed top ranked futures strategies. His core focus is (1) applying machine learning and developing systematic strategies, and (2) solving the toughest problems of discretionary trading by applying quantitative tools, machine learning, and performance discipline. You can contact the author at