Link Search Menu Expand Document

Technical Analysis (Machine Learning and Predictive Analytics in Finance)

Shahid Beheshti University | Faculty of Management and accounting | 1403_2

Syllabus 🧐

Course Objectives

In the era of Big Data, organizations have unprecedented access to vast amounts of information, and those that can effectively harness this data to uncover meaningful patterns and make data-driven decisions gain a significant competitive edge. This course explores the interdisciplinary field of analytics in finance, combining data science, machine learning, and predictive modeling to extract insights and make accurate predictions.

The course emphasizes the power of models in helping us understand financial data. These models not only provide insights but also predict important variables such as price, sales, and risk. For instance, they can forecast future values like next quarter’s product sales, which are crucial for strategic decision-making in finance.

Students will delve into both foundational and cutting-edge techniques in data science and analytics, with a focus on their applications in finance. The curriculum covers the entire machine learning workflow, including data transformation, model training, prediction, and evaluation. Key topics include exploratory data analysis, feature engineering, and result assessment, with particular attention to performance metrics, potential overfitting, and the bias-variance tradeoff.

The course will explore various application areas in finance, such as product pricing optimization, sales forecasting, market trend analysis, risk management, and portfolio optimization.

By the end of the course, students will have developed a comprehensive understanding of how organizations can utilize data science and analytics to develop competitive strategies in the financial sector. They will be equipped with the skills to transform raw financial data into actionable insights, driving informed decision-making and creating value in today’s data-driven financial landscape.

Learning Goals

Upon successful completion of this course, the student will be able to:

  1. Implement data-driven solutions for various financial applications, such as product pricing, sales forecasting, market trend analysis, risk management, and portfolio optimization.
  2. Utilize modern programming tools and libraries (e.g., Python, Pandas, Scikit-learn) for financial data analysis and machine learning.
  3. Understand the ethical considerations and potential biases in financial machine learning models.

Structure of the course

  • Meets Twice Weekly
    • Sunday, Tuesday 15:00 - 17:00
  • There will be several assignments throughout the course for students to practice the material covered.