交易核心数学体系：从概率统计到随机微积分完整路线图
THE MATH NEEDED FOR TRADING (COMPLETE ROADMAP):
提供了一套完整的交易数学方法论框架，涵盖从基础统计到高级随机微积分的可复用知识体系，适合希望系统化提升量化建模能力的从业者收藏参考。
THE MATH NEEDED FOR TRADING (COMPLETE ROADMAP):
交易所需的数学知识（完整路线图）：
today I'll will break down the essential math you need for trading & this is the exact roadmap that helped me personally
今天，我将为你拆解交易中必备的数学知识，这也是对我个人产生实际帮助的确切路线图。
when i started, i thought math was for interviews, two months into live trading i realized every position i took was pure math running in production
刚开始时，我以为数学只是为了面试；但在实盘交易两个月后，我意识到我做的每一笔仓位背后，都是纯粹的数学在运行。
here's the complete map of what math actually fires on real trades:
以下是真实交易中真正起作用的数学知识完整图谱：
1. statistics and probability
1. 统计学与概率论
every price move is signal plus randomness. statistics separates the two
每一次价格变动都是信号加上随机性。统计学的作用在于将二者区分开来。
what you need:
你需要掌握的内容：
> mean, median, expected value = EV formula (win% × avg win) - (loss% × avg loss) is what you're actually maximizing > variance and standard deviation = foundation of every position sizing formula, becomes volatility when applied to returns > correlation from -1 to +1 = tells you if strategies are actually independent > correlation 0.9 across 3 strategies = you have one strategy dressed as three > conditional probability = the biggest edge upgrade retail misses. P(win) = 55% unconditionally, but 70% when VIX < 15 > Bayes' theorem = how you update beliefs when new information arrives. never work with static beliefs > central limit theorem = why portfolio-level statistics behave cleaner than individual trades > linear and logistic regression = building blocks for mean reversion and binary prediction
> 均值、中位数、期望值 = EV 公式（胜率 × 平均盈利）-（败率 × 平均亏损），这才是你真正需要最大化的目标 > 方差和标准差 = 所有仓位管理公式的基础，应用于收益率时即转化为波动率 > 相关系数（从 -1 到 +1）= 告诉你策略之间是否真正独立 > 三个策略间的相关系数为 0.9 = 你实际上只有一个策略，只是披上了三件外衣 > 条件概率 = 散户最容易忽略的最大优势提升点。无条件胜率为 55%，但当 VIX < 15 时，胜率升至 70% > 贝叶斯定理 = 新信息出现时如何更新你的信念。永远不要使用静态的信念 > 中心极限定理 = 解释了为什么组合层面的统计数据比单笔交易表现得更加稳健 > 线性回归与逻辑回归 = 均值回归与二元预测的构建基础
2. linear algebra
2. 线性代数
the moment you hold multiple positions, you're doing linear algebra whether you know it or not
当你持有多头寸的那一刻，无论你是否意识到，你都在进行线性代数运算。
what you need:
你需要掌握的内容：
> scalars, vectors, matrices = your portfolio is a weighted sum of vectors > portfolio variance = w^T Σ w. not the sum of individual variances. one matrix operation > eigenvalues and eigenvectors = reveal where risk actually lives. in a 500-stock universe, top 5 eigenvectors explain 70% of variance. the other 495 are noise > PCA and SVD = reduce 50 correlated indicators into 5 independent factors explaining 90% of variation
> 标量、向量、矩阵 = 你的投资组合是向量的加权和 > 组合方差 = w^T Σ w。这不是各个资产方差的简单相加，而是一次矩阵运算 > 特征值与特征向量 = 揭示风险的实际所在。在包含 500 只股票的宇宙中，前 5 个特征向量解释了 70% 的方差，其余 495 个则是噪声 > PCA（主成分分析）与 SVD（奇异值分解）= 将 50 个高度相关的指标降维为 5 个独立因子，解释 90% 的变化
3. time series analysis
3. 时间序列分析
markets have memory. today's price depends on yesterday's. volatility clusters. trends persist
市场具有记忆性。今日的价格取决于昨日。波动率会聚集，趋势会持续。
what you need:
你需要掌握的内容：
> stationarity = assumption most statistical tests make, but markets aren't stationary, this is why strategies decay when regime shifts > autocorrelation = positive means momentum, negative means mean reversion, zero means random walk > ARIMA = framework for forecasting returns and volatility > GARCH = formalizes what every trader knows, volatility clusters. after a big move expect more volatility > cointegration = the foundation of pairs trading. two assets can both trend but their spread stays stationary
> 平稳性 = 大多数统计检验所依赖的假设，但市场并非平稳的，这就是为什么策略在 regime shifts（制度转换/市场环境变化）时会失效 > 自相关性 = 正相关意味着动量，负相关意味着均值回归，零相关意味着随机游走 > ARIMA = 用于预测收益率和波动率的框架 > GARCH = 形式化了每个交易者都知道的事实：波动率聚集。大幅波动之后，预期会有更高的波动率 > 协整 = 配对交易的基石。两只资产可能各自呈现趋势，但它们之间的价差保持平稳
4. risk management math
4. 风险管理数学
edge doesn't matter if you size wrong
如果仓位 sizing 错误，优势（edge）毫无意义
what you need:
你需要掌握：
> Value at Risk = 95% VaR of $5,000 means 95% of the time you won't lose more, but 5% of the time you might lose much more > Sharpe ratio = (return - risk-free rate) / volatility. institutional threshold is Sharpe > 1.5 before deployment > maximum drawdown = biggest peak-to-trough loss. more intuitive than volatility for most traders > Monte Carlo simulation = randomizes trade sequencing to show the range of possible outcomes > Kelly criterion = f* = (bp - q) / b. professionals use 0.25x to 0.5x fractional Kelly because your true edge is never certain
> 风险价值（VaR）= 95% VaR 为 $5,000，意味着 95% 的情况下你不会亏损超过此金额，但 5% 的情况下你可能会亏损更多 > 夏普比率 = (回报率 - 无风险利率) / 波动率。机构在部署前的门槛通常是夏普比率 > 1.5 > 最大回撤 = 从峰值到谷值的最大损失。对于大多数交易者来说，这比波动率更直观 > 蒙特卡洛模拟 = 随机化交易序列以展示可能结果的分布范围 > 凯利公式 = f* = (bp - q) / b。专业人士使用 0.25x 到 0.5x 的分数凯利，因为你的真实优势永远是不确定的
5. stochastic calculus (for options)
5. 随机微积分（用于期权）
if you trade options, every price on your screen came from a stochastic differential equation
如果你交易期权，你屏幕上显示的每一个价格都源自一个随机微分方程
what you need:
你需要掌握：
> Black-Scholes = dS = μS dt + σS dW. the underlying follows geometric Brownian motion > Ito's Lemma = why the σ² term exists. this is why gamma exists > Heston stochastic volatility = dv = κ(θ - v)dt + ξ√v dW. captures the volatility smile that Black-Scholes misses > delta hedging = stochastic calculus running in production. every rehedge is dictated by the SDE governing the underlying
> Black-Scholes = dS = μS dt + σS dW。标的资产遵循几何布朗运动 > 伊藤引理 = 解释了为什么存在 σ² 项。这也是为什么存在 gamma 的原因 > Heston 随机波动率模型 = dv = κ(θ - v)dt + ξ√v dW。捕捉了 Black-Scholes 模型遗漏的波动率微笑 > Delta 对冲 = 在生产环境中运行的随机微积分。每次重新对冲都由支配标的资产的 SDE 决定
MINIMUM TO START
起步所需的最小知识
you don't need everything above to start
你不需要掌握上述所有内容才能开始
for your first backtest:
对于你的第一次回测：
> mean, median, standard deviation > correlation > basic probability > Sharpe ratio and max drawdown
> 均值、中位数、标准差 > 相关性 > 基础概率论 > 夏普比率和最大回撤
start with statistics, that alone separates you from 95% of retail traders
从统计学开始，仅此一点就能让你与 95% 的散户交易者区分开来
every real trade is math executing in production:
每一笔真实的交易都是在生产环境中执行的数学：
> entry = conditional probability > validation = statistics > portfolio = linear algebra > sizing = Kelly optimization > risk = VaR, Sharpe, max drawdown > options = stochastic calculus
> 入场 = 条件概率 > 验证 = 统计学 > 投资组合 = 线性代数 > 仓位 sizing = 凯利优化 > 风险管理 = VaR、夏普比率、最大回撤 > 期权 = 随机微积分
the traders who make consistent money see markets as continuous equations, everyone else guesses
能够持续盈利的交易者将市场视为连续的方程，而其他人则在猜测
if you're a complete beginner shoot me a DM and I'll share the resources with you
如果你是完全的新手，请私信我，我会与你分享资源
MATH IS EVERYTHING <3
数学是一切 <3
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力