{"topic":{"id":15350,"title":"Quantitative Trading Summary – Headlands Technologies LLC Blog","slug":"topic","categoryId":4,"createdAt":"2026-01-04 02:59:54.914431","bumpedAt":"2026-01-04 05:55:05.773748","views":146,"postsCount":2,"highestPostNumber":2,"likeCount":0,"closed":false,"pinned":false,"excerpt":"https://blog.headlandstech.com/2017/08/03/quantitative-trading-summary/ 从这篇博文里能学到很多东西，中间 Market Taking vs Market Making, Market microstructure signals 两部分没看懂，让 AI 给我解释了一下： Market Maker (做市商) = 餐厅老板角色:提供流动性，等待别人来交易怎么赚钱:…","deletedAt":null,"isAnonymous":false,"category":{"id":4,"name":"谈笑风生","slug":"general","color":"25AAE2"},"author":{"id":7075,"username":"jbden","name":null,"avatarUrl":"/uploads/image/1e/8b/1e8bab3b6f297391fe23ceb66e7a57cad9bc903396007c9a08d6536889e5dcfe.avif"},"tags":[]},"posts":[{"id":69752,"postNumber":1,"raw":"https://blog.headlandstech.com/2017/08/03/quantitative-trading-summary/\n\n从这篇博文里能学到很多东西，中间 Market Taking vs Market Making, Market microstructure signals 两部分没看懂，让 AI 给我解释了一下：\n\n\n\n## **Market Maker (做市商)** = 餐厅老板\n\n* **角色**:提供流动性，等待别人来交易\n* **怎么赚钱**:买卖价差 (bid-ask spread)\n* **具体操作**:\n * 同时挂买单 ($99) 和卖单 ($101)\n * 等别人来成交\n * 赚中间的$2差价\n* **承担风险**:持有库存的风险 (价格可能突然大跌)\n* **比喻**:像餐厅老板，准备好食材，等顾客上门\n\n## **Market Taker (吃单者)** = 顾客\n\n* **角色**:主动消耗流动性，立即成交\n* **怎么赚钱**:预测价格即将变动，抢先交易\n* **具体操作**:\n * 看到市场上有人卖$101\n * 预测价格会涨到$105\n * 立即以$101 买入 (支付 spread)\n * 等价格涨上去再卖出\n* **承担风险**:预测错误的风险\n* **比喻**:像急着吃饭的顾客，愿意支付餐厅的加价\n\n## **关键区别**\n\n|维度|Market Maker|Market Taker|\n| --- | --- | --- |\n|订单类型|**被动订单**(limit orders)|**主动订单**(market orders)|\n|速度要求 | 相对较低|**必须快**(抢在价格变动前)|\n|收益来源 | 赚 spread|赚价格变动 |\n|队列位置 | 很重要 (排前面先成交)|不太重要 (反正是主动吃单)|\n\n## **你提到的\"queue position\"**\n\n对 Market Maker 来说，queue position**极其重要**:\n\n* 如果你的$99 买单排在第 1 位，大单来了你先成交\n* 如果排在第 1000 位，轮不到你\n\n对 Market Taker 来说，queue position 意义不大:\n\n* 你本来就是主动去\"吃掉\"别人挂的单\n\n* 不需要排队等别人来成交你的单\n\n**简单记忆**:Market Maker 是\"摆摊的\",Market Taker 是\"买东西的\"。摆摊位置 (queue) 很重要，买东西就直接去摊位买就行了。\n\n这样理解了吗？\n\n---\n\n## Market microstructure signals\n## What is this system doing?\n\nThink of it as a super-fast robot trader that watches the market and tries to predict where prices are going in the next few milliseconds, then buys or sells to make small profits.\n\n## The Three Main Parts\n\n**1. Input: Market Data (What's happening right now?)**\n\nThe system receives constant updates from the exchange about three things:\n\n* **Someone wants to buy/sell** - A new order appears (e.g., \"I'll buy 10 shares at $98.75\")\n* **Someone cancels their order** - An order disappears\n* **A trade happens** - A buyer and seller actually exchange shares\n\nThese updates build an **order book**, which shows all pending buy and sell orders at different prices. Think of it like a two-sided auction board.\n\n**2. The Strategy: Reading the \"Signals\"**\n\nThe system uses patterns in the order book to guess where the price will go next. Here are the three signals explained:\n\n**Book Pressure** - \"Which side is heavier?\"\n\n* If there are more/bigger buy orders than sell orders, the price will probably go up\n* It's like a tug-of-war: the heavier side usually wins\n* The calculation creates a weighted average that leans toward the stronger side\n\n**Trade Impulse** - \"Momentum matters\"\n\n* If you see a big sell trade, there's often another sell trade coming immediately after\n* Why? Multiple traders might react to the same news at almost the same time\n* It's like dominos falling - one trade often triggers similar trades\n\n**Related Trade** - \"What are similar stocks doing?\"\n\n* If a related stock (like Pepsi when you're trading Coke) just moved, yours probably will too\n* Uses correlation between securities\n\n**3. Output: Making a Trade**\n\nThe system combines these signals into a \"theoretical price\" - what it thinks the true value is right now. If this price is different enough from the market price, it places an order to capture the difference.\n\n## The Example Walkthrough\n\nThe document shows a situation where:\n\n* A big sell trade happens (9 shares)\n* This creates trade impulse (momentum down)\n* But it also removes buy orders, changing book pressure\n* Combined, the theoretical price drops to $98.64\n* But someone still wants to buy at $98.75\n* So the system sells to them for an instant $0.11 profit per share!\n\n## Why This Works (or worked)\n\nThis strategy makes money by being faster and smarter than other traders at processing information that's already public. However, as the document hints, this *used* to work better - nowadays everyone has similar systems, so the edges are much smaller and you need to be extremely fast and sophisticated to compete.","cooked":"

https://blog.headlandstech.com/2017/08/03/quantitative-trading-summary/

从这篇博文里能学到很多东西，中间 Market Taking vs Market Making, Market microstructure signals 两部分没看懂，让 AI 给我解释了一下：

Market Maker (做市商) = 餐厅老板

角色:提供流动性，等待别人来交易
怎么赚钱:买卖价差 (bid-ask spread)
具体操作:\n
- 同时挂买单 ($99) 和卖单 ($101)
- 等别人来成交
- 赚中间的$2差价
\n
承担风险:持有库存的风险 (价格可能突然大跌)
比喻:像餐厅老板，准备好食材，等顾客上门

Market Taker (吃单者) = 顾客

角色:主动消耗流动性，立即成交
怎么赚钱:预测价格即将变动，抢先交易
具体操作:\n
- 看到市场上有人卖$101
- 预测价格会涨到$105
- 立即以$101 买入 (支付 spread)
- 等价格涨上去再卖出
\n
承担风险:预测错误的风险
比喻:像急着吃饭的顾客，愿意支付餐厅的加价

关键区别

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

维度	Market Maker	Market Taker
订单类型	被动订单(limit orders)	主动订单(market orders)
速度要求	相对较低	必须快(抢在价格变动前)
收益来源	赚 spread	赚价格变动
队列位置	很重要 (排前面先成交)	不太重要 (反正是主动吃单)

你提到的\"queue position\"

对 Market Maker 来说，queue position极其重要:

如果你的$99 买单排在第 1 位，大单来了你先成交
如果排在第 1000 位，轮不到你

对 Market Taker 来说，queue position 意义不大:

\n
你本来就是主动去\"吃掉\"别人挂的单
\n
\n
不需要排队等别人来成交你的单
\n

简单记忆:Market Maker 是\"摆摊的\",Market Taker 是\"买东西的\"。摆摊位置 (queue) 很重要，买东西就直接去摊位买就行了。

这样理解了吗？

Market microstructure signals

What is this system doing?

Think of it as a super-fast robot trader that watches the market and tries to predict where prices are going in the next few milliseconds, then buys or sells to make small profits.

The Three Main Parts

1. Input: Market Data (What's happening right now?)

The system receives constant updates from the exchange about three things:

Someone wants to buy/sell - A new order appears (e.g., \"I'll buy 10 shares at $98.75\")
Someone cancels their order - An order disappears
A trade happens - A buyer and seller actually exchange shares

These updates build an order book, which shows all pending buy and sell orders at different prices. Think of it like a two-sided auction board.

2. The Strategy: Reading the \"Signals\"

The system uses patterns in the order book to guess where the price will go next. Here are the three signals explained:

Book Pressure - \"Which side is heavier?\"

If there are more/bigger buy orders than sell orders, the price will probably go up
It's like a tug-of-war: the heavier side usually wins
The calculation creates a weighted average that leans toward the stronger side

Trade Impulse - \"Momentum matters\"

If you see a big sell trade, there's often another sell trade coming immediately after
Why? Multiple traders might react to the same news at almost the same time
It's like dominos falling - one trade often triggers similar trades

Related Trade - \"What are similar stocks doing?\"

If a related stock (like Pepsi when you're trading Coke) just moved, yours probably will too
Uses correlation between securities

3. Output: Making a Trade

The system combines these signals into a \"theoretical price\" - what it thinks the true value is right now. If this price is different enough from the market price, it places an order to capture the difference.

The Example Walkthrough

The document shows a situation where:

A big sell trade happens (9 shares)
This creates trade impulse (momentum down)
But it also removes buy orders, changing book pressure
Combined, the theoretical price drops to $98.64
But someone still wants to buy at $98.75
So the system sells to them for an instant $0.11 profit per share!

Why This Works (or worked)

This strategy makes money by being faster and smarter than other traders at processing information that's already public. However, as the document hints, this used to work better - nowadays everyone has similar systems, so the edges are much smaller and you need to be extremely fast and sophisticated to compete.

\n","createdAt":"2026-01-04 02:59:55.050818","updatedAt":"2026-01-04 03:04:42.803115","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":1001,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":2,"publicVersion":2,"deletedAt":null,"isAnonymous":false,"user":{"id":7075,"username":"jbden","name":null,"avatarUrl":"/uploads/image/1e/8b/1e8bab3b6f297391fe23ceb66e7a57cad9bc903396007c9a08d6536889e5dcfe.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}},{"id":69753,"postNumber":2,"raw":"The industry has generally settled on three main types of strategies that are sustainable because they provide real economic value to the market:\n\n* Arbitrage: Arbitrage and its economic benefits have been well understood for quite some time and documented by academia. The companies that are still competitive in arbitrage have one of 3 advantages:\n * Scale: To determine that some complex option or futures spread products are mispriced relative to a set of others, nontrivial calculations must be performed, including the fee per leg, and then the hedged position has to be held and margined until expiry. Being able to manage this and have low fees requires scale.\n * Speed: Speed either comes from having faster telco or being able to hedge. For example, triangular arbitrage on FX products traded in London, NY, and Japan and are a major impetus for the Go West and Hibernia microwave telecom projects. Arbitrageurs rely on the speed of their order gateway connections so they can hedge on related markets if they are overfilled.\n * Queue position: Being able to enter one leg of an arbitrage by passively buying on the bid or selling on the offer reduces costs by not having to cross the spread on that leg, so being able to achieve good queue position can give an edge in arb trades.\n* Market Taking: Placing a marketable buy or sell order to profit from a predicted price change. The economic value market takers are being paid for is either:\n * properly pricing the relative value of related securities\n * trading and thereby contributing to price discovery in products after observed changes in supply and demandLike a real estate negotiation that can change a deal’s value minute-by-minute when negotiators come to the table face-to-face and discover each other’s positions, even though the fundamentals of the deal or real estate market certainly don’t fluctuate by the minute, market takers are the high-stakes-mediators of the trading world. Market taking requires predictive signals and relatively low-latency because you pay to cross the spread. A common low-latency market taking strategy would be to attempt to buy the remaining liquidity at a price after a large buy trade.\n\n* Market Making: Posting passive non-marketable buy and sell orders with the goal to profit from the spread. The economic value market makers are being paid for is connecting buyers and sellers who don’t arrive at the market at the same time. Market makers are compensated for the risk that there may be more buyers than sellers or vice versa for an extended time, such as during times of market stress.\n\n解释一下这三个，尤其是后两者的区别\n\n---\n## AI Answser:\n\n我来详细解释这三种策略，特别是后两者的区别：\n\n## 三种策略概述\n\n**1. 套利（Arbitrage）** 利用同一资产或相关资产在不同市场/形式间的价格差异获利。本质上是\"无风险\"交易，同时买入低价卖出高价。需要的优势是规模、速度或队列位置。\n\n**2. 市场攫取（Market Taking）** 主动发出可成交订单（吃单），预测价格变动来获利。你支付买卖价差的成本来立即成交。\n\n**3. 市场做市（Market Making）** 被动挂出限价订单（挂单），通过赚取买卖价差获利。你提供流动性，等待别人来成交你的订单。\n\n## Market Taking vs Market Making 的核心区别\n\n### **谁支付价差？**\n\n* **Market Taking**: 你支付价差成本。你用市价单\"穿越\"买卖价差来立即成交\n* **Market Making**: 你赚取价差收益。你同时挂买单和卖单，从两边的差价中获利\n\n### **主动 vs 被动**\n\n* **Market Taking**: 主动进攻型。你认为价格即将变动，所以愿意支付成本来立即建仓\n* **Market Making**: 被动防守型。你在买卖两边挂单等待，不预测方向\n\n### **盈利来源**\n\n* **Market Taking**: 预测能力 - 你必须正确预测价格走向才能弥补价差成本并盈利\n* **Market Making**: 流动性服务 - 你连接了不同时间到达的买卖双方，承担库存风险换取价差\n\n### **风险特征**\n\n* **Market Taking**: 方向性风险 - 如果价格预测错误就亏损\n* **Market Making**: 库存风险 - 在市场压力期间可能积累单边头寸（比如都是卖家没有买家）\n\n### **举个例子**\n\n假设某股票当前报价：买入 $100.00 / 卖出 $100.10\n\n**Market Taker 的行为：** 看到大额买单出现，预测价格将上涨，立即以 $100.10 买入（支付了 $0.10 的价差成本），期望很快能以 $100.50 或更高价格卖出获利。\n\n**Market Maker 的行为：** 在 $100.00 挂买单，$100.10 挂卖单。如果有人以 $100.00 卖给他，然后另一个人以 $100.10 从他这买走，他赚取 $0.10 的价差。他不预测方向，只是提供流动性服务。\n\n### **文中提到的关键点**\n\nMarket Taking 像\"高风险调解人\"的比喻很形象：就像房地产谈判中，当谈判者面对面发现彼此立场时，即使房地产市场基本面并未按分钟波动，但交易价值却可能分分钟变化。Market Taker 就是捕捉这些瞬时供需变化的人。\n\nMarket Making 的价值在于\"连接不同时间到达市场的买卖双方\" - 这是时间维度上的服务。","cooked":"

The industry has generally settled on three main types of strategies that are sustainable because they provide real economic value to the market:

\n
Arbitrage: Arbitrage and its economic benefits have been well understood for quite some time and documented by academia. The companies that are still competitive in arbitrage have one of 3 advantages:
\n
- Scale: To determine that some complex option or futures spread products are mispriced relative to a set of others, nontrivial calculations must be performed, including the fee per leg, and then the hedged position has to be held and margined until expiry. Being able to manage this and have low fees requires scale.
- Speed: Speed either comes from having faster telco or being able to hedge. For example, triangular arbitrage on FX products traded in London, NY, and Japan and are a major impetus for the Go West and Hibernia microwave telecom projects. Arbitrageurs rely on the speed of their order gateway connections so they can hedge on related markets if they are overfilled.
- Queue position: Being able to enter one leg of an arbitrage by passively buying on the bid or selling on the offer reduces costs by not having to cross the spread on that leg, so being able to achieve good queue position can give an edge in arb trades.
\n
\n
Market Taking: Placing a marketable buy or sell order to profit from a predicted price change. The economic value market takers are being paid for is either:
\n
- properly pricing the relative value of related securities
- trading and thereby contributing to price discovery in products after observed changes in supply and demandLike a real estate negotiation that can change a deal’s value minute-by-minute when negotiators come to the table face-to-face and discover each other’s positions, even though the fundamentals of the deal or real estate market certainly don’t fluctuate by the minute, market takers are the high-stakes-mediators of the trading world. Market taking requires predictive signals and relatively low-latency because you pay to cross the spread. A common low-latency market taking strategy would be to attempt to buy the remaining liquidity at a price after a large buy trade.
\n
\n
Market Making: Posting passive non-marketable buy and sell orders with the goal to profit from the spread. The economic value market makers are being paid for is connecting buyers and sellers who don’t arrive at the market at the same time. Market makers are compensated for the risk that there may be more buyers than sellers or vice versa for an extended time, such as during times of market stress.
\n

解释一下这三个，尤其是后两者的区别

AI Answser:

我来详细解释这三种策略，特别是后两者的区别：

三种策略概述

1. 套利（Arbitrage） 利用同一资产或相关资产在不同市场/形式间的价格差异获利。本质上是\"无风险\"交易，同时买入低价卖出高价。需要的优势是规模、速度或队列位置。

2. 市场攫取（Market Taking） 主动发出可成交订单（吃单），预测价格变动来获利。你支付买卖价差的成本来立即成交。

3. 市场做市（Market Making） 被动挂出限价订单（挂单），通过赚取买卖价差获利。你提供流动性，等待别人来成交你的订单。

Market Taking vs Market Making 的核心区别

谁支付价差？

Market Taking: 你支付价差成本。你用市价单\"穿越\"买卖价差来立即成交
Market Making: 你赚取价差收益。你同时挂买单和卖单，从两边的差价中获利

主动 vs 被动

Market Taking: 主动进攻型。你认为价格即将变动，所以愿意支付成本来立即建仓
Market Making: 被动防守型。你在买卖两边挂单等待，不预测方向

盈利来源

Market Taking: 预测能力 - 你必须正确预测价格走向才能弥补价差成本并盈利
Market Making: 流动性服务 - 你连接了不同时间到达的买卖双方，承担库存风险换取价差

风险特征

Market Taking: 方向性风险 - 如果价格预测错误就亏损
Market Making: 库存风险 - 在市场压力期间可能积累单边头寸（比如都是卖家没有买家）

举个例子

假设某股票当前报价：买入 $100.00 / 卖出 $100.10

Market Taker 的行为： 看到大额买单出现，预测价格将上涨，立即以 $100.10 买入（支付了 $0.10 的价差成本），期望很快能以 $100.50 或更高价格卖出获利。

Market Maker 的行为： 在 $100.00 挂买单，$100.10 挂卖单。如果有人以 $100.00 卖给他，然后另一个人以 $100.10 从他这买走，他赚取 $0.10 的价差。他不预测方向，只是提供流动性服务。

文中提到的关键点

Market Taking 像\"高风险调解人\"的比喻很形象：就像房地产谈判中，当谈判者面对面发现彼此立场时，即使房地产市场基本面并未按分钟波动，但交易价值却可能分分钟变化。Market Taker 就是捕捉这些瞬时供需变化的人。

Market Making 的价值在于\"连接不同时间到达市场的买卖双方\" - 这是时间维度上的服务。

\n","createdAt":"2026-01-04 05:55:05.773748","updatedAt":"2026-01-04 05:56:08.718972","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":1210,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":7075,"username":"jbden","name":null,"avatarUrl":"/uploads/image/1e/8b/1e8bab3b6f297391fe23ceb66e7a57cad9bc903396007c9a08d6536889e5dcfe.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}}],"hasMore":false,"lastReadPostNumber":1,"hasUrlPostNumber":false}