20568 - EMPIRICAL METHODS FOR INNOVATION STRATEGIES
Course taught in English
Go to class group/s: 31
Class-group lessons delivered on campus
Basic computer literacy. Install tools needed for Python programming (instructions given before class starts).
This course provides the students with the tools and methods to produce empirical evidence to support decision-making processes in firms and it is designed for whoever wants to use these methods in practice to solve concrete managerial problems. The initial part of the course reviews the basic tools and technique for data analysis, including introduction to Stata and Python, to put each student at the level of students who have already worked on these techniques. For attending students, the course then focuses on a group project that represents the main goal and learning tool of the course. In this respect, the course is an advanced course that teaches mainly through practical applications of the concepts and material. The methods, goals and projects of the course are broad enough to deal with and apply to different managerial problems and contexts, from marketing to entrepreneurial decisions, innovation, firm strategy, business models. Along with the main group project the course features the use of data made available to the students to address concrete managerial problems and questions. The course also develops an important focus on the use of textual data, large data-set, and machine learning techniques.
- A summary of tools to make data-driven managerial decisions: from correlation and tests of hypotheses to regressions and causal relations.
- Advanced tools (textual analysis, machine learning).
- Group project.
- Data analyses and exercises.
Expected Teaching Schedule
|1||Python 1: variables and strings|
|2||Python 2: lists and sets|
|3||Python 3: dictionaries|
|4||Python 4: if-statements|
|5||Python 5: for-loops|
|6||Python 6: text classification|
|MID TERM BREAK|
|15||Tobit & Diff in Diff|
|19||Final project consultation|
|21||Final project consultation|
|23||Final project presentations|
|24||Final project presentations|
- Learn how to use Python to make data-driven managerial decisions.
- Learn how to use econometric tools in practice using large datasets.
- Understand the basis to make data-driven managerial decisions.
- Face-to-face lectures
- Exercises (exercises, database, software etc.)
- Group assignments
- Interactive class activities (role playing, business game, simulation, online forum, instant polls)
For attending students learning in the course depends mostly on the development of a group project throughout the course. The group project employs real data to address a concrete managerial problem. Lectures, discussions in class about the projects developed by each group enhance the learning opportunities of the attending students.
|Continuous assessment||Partial exams||General exam|
- Group project accounts for about 60%
- Individual assessments for about 40%.
The evaluation of the attending students is based on three in-class exercises plus a final empirical project produced in groups and presented in class. You will be considered as an attending student if you complete the exercises and submit the final project. In-class attendance will NOT be taken. However, class attendance is strongly encouraged. In the past, students who show up to class have out-performed those who do not by a substantial margin.
Expected grading scheme
|Best 2 out of 3 in-class exercises||10|
|Final project report||12|
|Final project presentation||3|
|Project peer evaluation||5|
|Bonus: Usage of data from proprietary databases subscribed to by Bocconi Library. Examples include Compustat, Bloomberg, etc. You are allowed to use non-proprietary and publicly available databases from the internet for your project - but you will not get the bonus point.||1|
The evaluation of the non-attending students will be based on a closed book written exam consisting of questions on both the theoretical and programming aspects of the course. In the past, non-attending students have performed poorly in this course.
- Lecture slides.
- General references for some of the more technical material (not required for the exam, but useful for consultation).
- Jupyter notebooks.
- Lecture slides and references to specific articles and similar material.
General references for some of the more technical material (not required for the exam, but useful for consultation).