第一节 Algorithmic Trading In Python Overview(Python量化交易概述)
课程介绍overview
1.what is algo-trading? Compare to retail traders
(对于散户来说,量化交易是什么?)
2.why Python? Python notebook简介
(Python应用于量化交易的优势)
3.交易系统简介
4.Python for finance常用packages : numpy, scipy, pandas, statsmodel, scikit-learn, matplotlib
(Python在金融中的应用以及各种库函数)
5.量化交易的就业分析和职业发展
第二节 Python for Finance 常用packages 学习I
1.学习数据分析基础 library (库) -- NumPy:
● Creating Arrays(创建数组)
● Using Arrays and Scalars(使用数组和标量)
● Indexing Arrays(索引数组)
● Array Manipulation(数组操作)
● Array Functions(数组函数)
2.学习数据分析高阶 library – Pandas:
● DataFrames and file reading(DataFrames和文件阅读导入)
● Index and Reindex Objects, Index Hierarchy(索引和索引命令对象,索引的层次结构)
● Select/Drop Entry(选择/删除条目)
● Data Alignment, Rank and Sort、Handling missing data(数据对齐、等级和排序,处理缺失数据 )
● Summary Statistics(汇总统计)
3. 统计分析和最优化 library—scipy
● Optimization(优化)
● Statistical test(统计检验)
● Linear algebra-linalg (线性代数)
4. 画图 library—matplotlib
● How to plot basic graphs for different types
(如何绘制基本图形为不同的类型)
● How to plot multiple graphs and do arrangement
(如何绘制多个图形并进行排列)
● Advanced plotting
(高级绘图/数据可视化)
第三节 Python for Finance 常用packages 学习 II
1.统计模型library--statsmodel
● Regression and generalized regression models
(回归和广义回归模型)
● Time series analysis (时间序列分析)
● Statistical test(统计检验)
● Distributions (分布)
2.金融数据处理
● Frequency of data(数据的频率)
● How to source data from Bloomberg、Yahoo Finance and so on
(如何得到源数据)
● Data quality check and cleaning(smooth, seasonality adjustment, fill-forward and so on)(数据质量检查和清理)
第四节 金融数据建模与预测/风险测度因子
1.Statistical learning and techniques overview
(统计学习和技术概述)
2.Financial time series analysis
(金融时间序列分析)
3.Forecasting measures and techniques overview
(预测措施和技术概述)
4.Performance evaluation and risk measures
(绩效评估和风险评估度量)
第五节传统量化交易策略和Python实现
1.Event-driven trading strategies and implementation
(事件驱动的交易策略和实施)
2. Statistical trading strategies and implementation
(统计交易策略和实施)
● Moving-average trade(移动平均交易)
● Pair trading (配对交易)
3. Parameter optimization(参数优化)
● Overfitting and cross-validation(过度拟合和交叉验证)
● Grid search(网格搜索)
第六节 高阶量化交易策略 I—贝叶斯模型
1.Advance algorithmic trading overview
(高级算法交易概述)
2. What is Bayesian statistics
(什么是贝叶斯统计)
3. Bayesian Inference methods
(贝叶斯推理方法)
4. Markov Chain Monte Carlo
(MCMC 马科夫链门特卡罗)
5. Linear regression model based on Bayes
(基于贝叶斯的线性回归模型)
6. Bayesian stochastic volatility model
(贝叶斯随机波动模型)
7. Python举例和模型代码实现
第七节 金融时间序列分析-I
1.序列相关系和random walk
(随机游走)
2.平稳时间序列模型-AR/MA/ARMA
(波动率预测模型)
3.非平稳时间序列模型-ARIMA/异方差模型-GARCH
第八节 金融时间序列分析-II
1.State-model and Kalman filter
(状态模型和卡尔曼滤波 )
● Kalman filter theory
(卡尔曼滤波器理论)
● Application to regression and pair trading in Python
(卡曼滤波器在回归及配对交易方面的应用)
2.Hidden Markov Models
(隐式马科夫模型)
● HMM theory (HMM理论)
● Application to market regime detection in Python
(HMM在市场机制判定/探测的应用)
第九节 机器学习于量化交易中的应用I
1.Introduction to machine learning
(机器学习介绍)
2.Linear regression and MLE
(线性回归和MLE)
3. Decision Tree(决策树)
● Entropy and information gain theories (熵与信息论基础)
● Pruning the tree(算法优化-减枝)
● Advanced tree methods—bagging, boosting, random forest and son on(高级树形理论)
4. Python implementation
(如何用Python实现)
第十节 机器学习于量化交易中的应用II
1.Introduction to Support Vector Machine
(支持向量机的介绍)
● Maximum margin classifier(最大边缘分类器)
● Linear SVM(线性支持向量机)
● Kernel function and higher dimension mapping(核函数与高维数据投影)
2. Cross-Validation for model selection
(交叉验证的模型选择)
● Leave one out (留一验证)
● K-fold
● Bias-variance trade-off(偏差-方差的折中)
第十一节 机器学习于量化交易中的应用III
1.Introduction to Clustering
(介绍集群 聚类)
● Clustering theory
(集群理论 聚类)
● Implementation to financial market
(在金融领域的应用)
2. Neural network
(神经网络)
● Introduction to artificial neural network(人工神经网络)
● Introduction to recurrent neural network(递归神经网络)
3. Unsupervised dimensional reduction techniques
(非监督降维技术)
● PCA/CCA
● Implementation to financial market
(在金融领域的应用)
第十二节 机器学习于量化交易中的应用IV
1. Introduction to QS Trader in Python
● QS Trader overview (QS Tader概况)
● QS Trader for backtesting (利用XXX的回测)
2. ARIMA+GARCH Trading
(XXX交易)
● Strategy on Stock Market (股票市场策略)
● Indexes Using R (用R语言做什么不明白问老师)
3. Cointegration-Based Pairs Trading using QSTrader
(基于QSTrader的协同一体化/结合下的配对交易)
4. Kalman Filter-Based Pairs Trading using QSTrader
(基于QSTrader的卡曼滤波配对交易)
5. Supervised Learning for Intraday Returns Prediction using QSTrader
(利用监督学习预测日间交易回报)
第十三节 Python for ODE PDE numerical methods (Python for 偏微分方程数值解)
1.ODE examples in Finance
(常微分方程金融例子)
2.Forward Backward Crank-Nicholson Methods for ODE
(向前向后CN方法)
3.Explicit Implicit and CN methods for PDE
(显式隐式CN方法)
4.Option pricing examples for PDE
(偏微分方程期权定价例子)
第十四节 Python衍生品定价-I
1. 蒙特卡洛模拟基础
2. 常见随机过程离散化
3. European Option(欧式期权)蒙特卡洛模拟定价
4. Exotic option
(奇异期权定价)
5.Least-square monte-carlo for American option pricing
(最小二乘蒙特卡罗对美式期权定价)
第十五节 Python衍生品定价-II
1.Common variance reduction techniques for Monte-Carlo and application to option pricing
(常见蒙特卡罗方差降低方法与期权定价)
2.Importance sampling and change of measure
(重点抽样级数和测度变化)
3.Incremental risk charge model and Gaussian Copula for credit risk
(信用风险的IRC模型和高斯核)