Quantitative Investment: Using Python as a Tool

Quantitative Investment: Using Python as a Tool is a fintech monograph by Cai Li Duan, published by Publishing House of Electronics Industry. It comprises 5 parts and 34 chapters in a 620-page 16-mo format, arranged from programming fundamentals to strategy implementation. Part 1 introduces Python, starting with interpreter installation, Anaconda environment setup, and the use of IPython and Spyder, then progressively covering object types such as numbers, strings, lists, tuples, dictionaries, and sets; operators, conditionals, and loops; functions and object-oriented programming; and on to NumPy multidimensional arrays, Pandas data processing, and Matplotlib visualization—equipping readers with the basic ability to handle financial data in Python. Part 2 covers statistics fundamentals: descriptive statistics, random variables, inferential statistics, analysis of variance, and regression analysis, providing the quantitative tools needed to read and implement later models. Part 3 moves into financial theory, portfolio construction, and quantitative stock selection, discussing measurement of asset returns and risk, portfolio theory and its extensions, the Capital Asset Pricing Model (CAPM), and the Fama-French three-factor model, with the corresponding calculations carried out in Python. Part 4 centers on time series and pairs trading, explaining basic time-series concepts, properties and forecasting methods, GARCH models, and approaches to constructing and testing pairs-trading strategies. Part 5 turns to technical indicators and quantitative investment, covering candlestick charts, momentum trading strategies, the RSI relative strength index, moving-average system strategies, channel breakout strategies, stochastic indicator trading strategies, volume-price relationship analysis, and OBV indicator trading strategies. The book's basic approach is to explain the method and reasoning first, then provide the corresponding Python code, so that readers can complete data processing, model computation, and strategy backtesting in the same environment. It is well suited as a transitional text on the path from programming basics to quantitative strategy implementation.