Big Data and Machine Learning in Quantitative Investment.
Tony. Guida
Bok Engelsk 2019 · Electronic books.
| Omfang | 1 online resource (299 pages)
|
|---|---|
| Opplysninger | Cover -- Title Page -- Copyright -- Contents -- Chapter 1 Do Algorithms Dream About Artificial Alphas? -- 1.1 Introduction -- 1.2 Replication or Reinvention -- 1.3 Reinvention with Machine Learning -- 1.4 A Matter of Trust -- 1.5 Economic Existentialism: A Grand Design or an Accident? -- 1.6 What is this System Anyway? -- 1.7 Dynamic Forecasting and New Methodologies -- 1.8 Fundamental Factors, Forecasting and Machine Learning -- 1.9 Conclusion: Looking for Nails -- Chapter 2 Taming Big Data -- 2.1 Introduction: Alternative Data - an Overview -- 2.1.1 Definition: Why 'alternative'? Opposition with conventional -- 2.1.2 Alternative is not always big and big is not always alternative -- 2.2 Drivers of Adoption -- 2.2.1 Diffusion of innovations: Where are we now? -- 2.3 Alternative Data Types, Formats and Universe -- 2.3.1 Alternative data categorization and definitions -- 2.3.2 How many alternative datasets are there? -- 2.4 How to Know What Alternative Data is Useful (And What isn't) -- 2.5 How Much Does Alternative Data Cost? -- 2.6 Case Studies -- 2.6.1 US medical records -- 2.6.2 Indian power generation data -- 2.6.3 US earnings performance forecasts -- 2.6.4 China manufacturing data -- 2.6.5 Short position data -- 2.6.6 The collapse of carillion - a use case example for alt data -- 2.7 The Biggest Alternative Data Trends -- 2.7.1 Is alternative data for equities only? -- 2.7.2 Supply-Side: Dataset Launches -- 2.7.3 Most common queries -- 2.8 Conclusion -- Reference -- Chapter 3 State of Machine Learning Applications in Investment Management -- 3.1 Introduction -- 3.2 Data, Data, Data Everywhere -- 3.3 Spectrum of Artificial Intelligence Applications -- 3.3.1 AI applications classification -- 3.3.2 Financial analyst or competitive data scientist? -- 3.3.3 Investment process change: An 'Autonomous Trading' case.. - 11.4.2 Model description -- 11.4.3 Model results -- 11.5 Conclusion -- References -- Chapter 12 Reinforcement Learning in Finance -- 12.1 Introduction -- 12.2 Markov Decision Processes: A General Framework for Decision Making -- 12.3 Rationality and Decision Making Under Uncertainty -- 12.4 Mean-Variance Equivalence -- 12.5 Rewards -- 12.5.1 The form of the reward function for trading -- 12.5.2 Accounting for profit and loss -- 12.6 Portfolio Value Versus Wealth -- 12.7 A Detailed Example -- 12.7.1 Simulation-based approaches -- 12.8 Conclusions and Further Work -- References -- Chapter 13 Deep Learning in Finance: Prediction of Stock Returns with Long Short-Term Memory Networks -- 13.1 Introduction -- 13.2 Related Work -- 13.3 Time Series Analysis in Finance -- 13.3.1 Multivariate time series analysis -- 13.3.2 Machine learning models in finance -- 13.4 Deep Learning -- 13.4.1 Deep learning and time series -- 13.5 Recurrent Neural Networks -- 13.5.1 Introduction -- 13.5.2 Elman recurrent neural network -- 13.5.3 Activation function -- 13.5.4 Training recurrent neural networks -- 13.5.5 Loss function -- 13.5.6 Cost function -- 13.5.7 Gradient descent -- 13.6 Long Short-Term Memory Networks -- 13.7 Financial Model -- 13.7.1 Return series construction -- 13.7.2 Evaluation of the model -- 13.7.3 Data and results -- 13.8 Conclusions -- References -- Biography -- EULA.. - 3.3.4 Artificial intelligence and strategies development -- 3.4 Interconnectedness of Industries and Enablers of Artificial Intelligence -- 3.4.1 Investments in development of AI -- 3.4.2 Hardware and software development -- 3.4.3 Regulation -- 3.4.4 Internet of things -- 3.4.5 Drones -- 3.4.6 Digital transformation in steps - case study -- 3.5 Scenarios for Industry Developments -- 3.5.1 Lessons from autonomous driving technology -- 3.5.2 New technologies - new threats -- 3.5.3 Place for discretionary management -- 3.6 For the Future -- 3.6.1 Changing economic relationships -- 3.6.2 Future education focus -- 3.7 Conclusion -- References -- Chapter 4 Implementing Alternative Data in an Investment Process -- 4.1 Introduction -- 4.2 The Quake: Motivating the Search for Alternative Data -- 4.2.1 What happened? -- 4.2.2 The next quake? -- 4.3 Taking Advantage of the Alternative Data Explosion -- 4.4 Selecting A Data Source for evaluation -- 4.5 Techniques for Evaluation -- 4.6 Alternative Data for Fundamental Managers -- 4.7 Some Examples -- 4.7.1 Example 1: Blogger sentiment -- 4.7.2 Example 2: Online consumer demand -- 4.7.3 Example 3: Transactional data -- 4.7.4 Example 4: ESG -- 4.8 Conclusions -- References -- Chapter 5 Using Alternative and Big Data to Trade Macro Assets -- 5.1 Introduction -- 5.2 Understanding General Concepts Within Big Data and Alternative Data -- 5.2.1 What is big data? -- 5.2.2 Structured and unstructured data -- 5.2.3 Should you use unstructured or structured datasets? -- 5.2.4 Is big data also alternative data? -- 5.2.5 Legal questions around distributing alternative datasets -- 5.2.6 How much is an alternative dataset worth? -- 5.3 Traditional Model Building Approaches and Machine Learning -- 5.3.1 What is machine learning? -- 5.3.2 Difference between traditional machine learning and deep learning.. - 5.4 Big Data and Alternative Data: Broad-Based Usage in Macro-Based Trading -- 5.4.1 How do we use big data and alternative data in a macro context? -- 5.4.2 Real-life examples of big data and alternative datasets -- 5.5 Case Studies: Digging Deeper into Macro Trading with Big Data and Alternative Data -- 5.5.1 Federal reserve: Cuemacro federal reserve sentiment index for FX and bonds -- 5.5.2 Machine-readable news: Bloomberg news to understand price action in FX -- 5.5.3 Web traffic data: Using investopedia's anxiety index to understand market sentiment -- 5.5.4 Volatility data: Forecasting FX spot behaviour around scheduled events with a focus on BREXIT -- 5.6 Conclusion -- References -- Chapter 6 Big Is Beautiful: How Email Receipt Data Can Help Predict Company Sales -- 6.1 Introduction -- 6.2 Quandl's Email Receipts Database -- 6.2.1 Processing electronic receipts -- 6.2.2 The sample -- 6.3 The Challenges of Working with Big Data -- 6.4 Predicting Company Sales -- 6.4.1 Summary of our approach -- 6.4.2 A Bayesian approach -- 6.5 Real-Time Predictions -- 6.5.1 Our structural time series model -- 6.5.2 Estimation and prediction -- 6.6 A Case Study: http://Amazon.com Sales -- 6.6.1 Background -- 6.6.2 Results -- 6.6.3 Putting it all together -- 6.6.4 Real-time predictions -- References -- Chapter 7 Ensemble Learning Applied to Quant Equity: Gradient Boosting in a Multifactor Framework -- 7.1 Introduction -- 7.2 A Primer on Boosted Trees -- 7.3 Data and Protocol -- 7.3.1 Data -- 7.3.2 Features and labels engineering -- 7.3.3 Variables/Features used -- 7.4 Building the Model -- 7.4.1 Hyper-parameters -- 7.4.2 Cross-validation -- 7.4.3 Assessing the quality of the model -- 7.4.4 Variable importance -- 7.5 Results and Discussion -- 7.5.1 Time series analysis for equally-weighted decile portfolios -- 7.5.2 Further evidence of economic gains.. - 7.6 Conclusion -- References -- Chapter 8 A Social Media Analysis of Corporate Culture -- 8.1 Introduction -- 8.2 Literature Review -- 8.3 Data and Sample Construction -- 8.3.1 Description of online career community websites -- 8.3.2 Adding security identifiers to employee reviews -- 8.3.3 Validating the integrity of employee reviews -- 8.4 Inferring Corporate Culture -- 8.4.1 Data and summary statistics -- 8.4.2 Validating the goal measure -- 8.5 Empirical Results -- 8.6 Conclusion -- References -- Chapter 9 Machine Learning and Event Detection for Trading Energy Futures -- 9.1 Introduction -- 9.2 Data Description -- 9.2.1 Price data -- 9.3 Model Framework -- 9.3.1 Feature creation -- 9.4 Performance -- 9.4.1 Model portfolios -- 9.4.2 Variable importance -- 9.4.3 Ensemble portfolio -- 9.4.4 Ensemble portfolio - marginal contributions -- 9.4.5 Regime detection in the ensemble portfolio -- 9.5 Conclusion -- References -- Chapter 10 Natural Language Processing of Financial News -- 10.1 Introduction -- 10.2 Sources of News Data -- 10.2.1 Mainstream news -- 10.2.2 Primary source news -- 10.2.3 Social media -- 10.3 Practical Applications -- 10.3.1 Trading and investment -- 10.3.2 Sentiment analysis -- 10.3.3 Market making -- 10.3.4 Risk systems -- 10.4 Natural Language Processing -- 10.4.1 Preprocessing textual data -- 10.4.2 Representation of words as features -- 10.4.3 Inference -- 10.4.4 Evaluation -- 10.4.5 Example use case: Filtering merger arbitrage news -- 10.5 Data And Methodology -- 10.5.1 Results -- 10.5.2 Discussion -- 10.6 Conclusion -- References -- Chapter 11 Support Vector Machine-Based Global Tactical Asset Allocation -- 11.1 Introduction -- 11.2 Fifty Years of Global Tactical Asset Allocation -- 11.3 Support Vector Machine in the Economic Literature -- 11.3.1 Understanding SVM -- 11.4 A SVR-Based GTAA -- 11.4.1 Data.
|
| Emner | |
| Sjanger | |
| Dewey | |
| ISBN | 9781119522089
|
| ISBN(galt) |
