HU Credits: 3

Degree/Cycle: 2nd degree (Master)

Responsible Department: Business Administration

Semester: 1st Semester

Teaching Languages: English

Campus: Mt. Scopus

Course/Module Coordinator: ronen feldman

Coordinator Email: ronen.feldman@huji.ac.il

Coordinator Office Hours:

Teaching Staff:
Prof Ronen Feldman

Course/Module description:
The Course will teach the students the fundamentals needed to develop quant signals for stock trading based on structured and unstructured data. There will be extensive use of large language models and generative AI tools.

Course/Module aims:
The course is very practical and will provide the students with hands on experience based on the latest techniques used by the top hedge funds. The instructor spent the past several years in some of the top hedge funds and the materials covered in the course are based on his practical experience.

The students will get access to the following data sources:
1. SEC Filings (10K, 10Q, 8K)
2. Business News (Dow Jones)
3. Earning Call Transcripts
4. Social Media (stockswits)

The course will start with 2 classes that will gives a quick review of python programming so they can get up to speed.

Learning outcomes - On successful completion of this module, students should be able to:
The students will get raw signals based on earning call transcripts and company filings and will need to combine those with other fundamental signals and generate a combined model that outperforms the S&P 500. The students will also need to backtest the combined signal and visualize it to show its characteristics. The students will need to present in class their created signal and discuss in the detail the results of backtesting the signals.

Attendance requirements(%):
70%

Teaching arrangement and method of instruction: interactive learning with computers in the classroom. Reading of articles and discussions in class

Course/Module Content:
Python Refresh: 2 Classes
MODULE 1: DATA ANALYSIS WITH PANDAS (3 CLASSES)
• Dataframes
• Series and Panel Objects
• Operations
• Selecting and Slicing Data
• Plotting
• Application: Working with Financial Time Series
• Grouping Data
• Joining, Appending and Merging Data
• Application: Portfolio Analysis

MODULE 2: MACHINE LEARNING ALGORITHMS I (3 CLASSES)
• Parametric vs Non Parametric Models
• Feature Extraction
• Feature Engineering
• OLS Regression
• Lasso and Ridge
• Extending Parametric Models
• Polynomials
• Scaling
• Subset Selection
• Classification Algorithms
• Logistic Regression
• L1 and L2 Penalty
• Single and Multi-Class
• Clustering Algorithms (K-means, Hierarchical Clustering, DBScan)
• Application: Multi Class Modeling

MODULE 3: MACHINE LEARNING ALGORITHMS II (3 CLASSES)
• Non Parametric Models
• Financial Feature Engineering
• Unstructured Feature Extraction
• Decision Trees
• Support Vector Machines
• Assembling Methods
• Boosting
• Adaboost Algorithm
• Bagging
• Random Forest Algorithm
• Latest Advances:
• Extreme Gradient Boosting (XGB)


MODULE 4: TUNING ALGORITHMS (3 CLASSES)
• Cross Validation and Testing
• Financial BackTesting
• Pipelines and GridSearch
• Feature Engineering Practice
• Unstructured Feature Extraction
• Parallelization of processes
• Regression Practice
• Classification Practice
• Building Actual Signals

Required Reading:
Books:
Python for Data Analysis Second Edition
Advances in Financial Machine Learning

Papers:

1. INFORMATION, TRADING, AND VOLATILITY: EVIDENCE FROM FIRM-SPECIFIC NEWS
2. Antweiler, W., and M. Z. Frank, 2005, Is All That Talk Just Noise? The Information Content Of Internet Stock Message Boards, Journal of Finance 59, 1259–1293.
3. Barber, B., and Odean, T., 2008. All that glitters: the effect of attention and news on the buying behavior of individual and institutional investors. Review of Financial Studies 21, 785–818.
4. Feldman, R., S. Govindaraj, J. Livnat, and B. Segal, 2010, Managements Tone Change, Post Earnings Announcement Drift And Accruals, Review of Accounting Studies 15, 915–953
5. Loughran, T., and B. McDonald, 2011, When Is A Liability Not A Liability? Textual Analysis, Dictionaries, And 10-Ks, Journal of Finance 66, 35–65.
6. Tetlock, P. C., 2010, Does Public Financial News Resolve Asymmetric Information?, Review of Financial Studies 23, 3520–3557.

Additional Reading Material:

Grading Scheme :
Essay / Project / Final Assignment / Home Exam / Referat 70 %
Presentation / Poster Presentation / Lecture/ Seminar / Pro-seminar / Research proposal 10 %
Submission assignments during the semester: Exercises / Essays / Audits / Reports / Forum / Simulation / others 20 %

Additional information: