Digital Economics - 297 - 2nd year of master's degree

Ects : 6

Enseignant responsable :
FABRICE ROSSI

Volume horaire : 36

Description du contenu de l'enseignement :

The course gives a thorough presentation of the machine learning field and follows this outline:

1. general introduction to machine learning and to its focus on predictive performances (running example: k-nearest neighbours algorithm)
2. machine learning as automated program building from examples (running example: decision trees)
3. machine learning as optimization: empirical risk minimizationlinks with maximum likelihood estimationsurrogate losses and extended machine learning settingsregularisation and kernel methods (support vector machines)
4. reliable estimation of performances: over fittingsplit samplesresampling (leave-one-out, cross-validation and bootstrap)ROC curve, AUC and other advanced measures
5. combining models: ensemble techniquesbagging and random forestsboosting
6. unsupervised learning: clustering (hierarchical clustering, k-means and variants, mixture models, density clustering)outlier and anomaly detection

Coefficient : 2

Pré-requis obligatoire :

• intermediate level in either Python or R. Students are expected to be able to perform standard data management tasks in Python or R, including, but not limited to: loading a data set from a CSV filerecoding and cleaning the data set implementing a simple data exploration strategy based on pivot table and on graphical representation
• intermediate level in statistics and probability. Students are expected to be familiar with: descriptive statisticsconditional probabilities and conditional expectationscore results from statistics: bias and variance concepts, strong law of large numbers, central limit theorem, etc.

Compétences à acquérir :

After attending the course the students will

• have a good understanding of the algorithmic and statistical foundations of the main machine learning techniques
• be able to select machine learning techniques adapted to a particular task (exploratory analysis with clustering methods, predictive analysis, etc.)
• be able to design a model selection procedure adapted to a particular task
• report the results of a machine learning project with valid estimation of the performances of their model

Mode de contrôle des connaissances :

• quizzes and tests during the course
• machine learning project

Ects : 3

Enseignant responsable :
FABRICE ROSSI

Volume horaire : 18

Description du contenu de l'enseignement :

The course is a practical one which leverages knowledge and skills gained in other courses. It consists in a series of meeting both in full class and in subgroups. The first meetings addresses general questions and methodology issues, will the following ones consist in direct tutoring.

Coefficient : 1

Pré-requis obligatoire :

Intermediate level in Python. Students are expected to be able to perform standard data management tasks in Python, including, but not limited to:

• loading data sets from several CSV files
• collecting online data using scrapping libraries
• recoding, cleaning and merging data sources intro a database
• implementing a simple data exploration strategy based on pivot table and on graphical representation

Intermediate level in Machine Learning (as provided by the Machine Learning course of the Master).

Compétences à acquérir :

After following this course, students will be able to implement a full data oriented project including:

• identifying a research question that can be addressed using multiple publicly available data sets
• designing and implementing a data collection process
• implementing the related data management tasks (data representation, merging, cleaning, etc.)
• designing and implementing a data exploration strategy to validate their approach (especially concerning data quality and information level)
• using machine learning algorithms to study the research question

Mode de contrôle des connaissances :

Project report and oral exam.

Ects : 6

Enseignant responsable :
ANNA CRETI
ANTOINE CHAPSAL

Volume horaire : 30

Description du contenu de l'enseignement :

Theory and practice of competition in network industries; antitrust issues; theory of network and network effects; two-sided platforms and pricing

Coefficient : 2

Pré-requis recommandés :

Industrial Organization

Pré-requis obligatoire :

Advanced Micro

Compétences à acquérir :

Understanding of competition and regulation issues in network and digital economics

Mode de contrôle des connaissances :

Written exam

Bibliographie-lectures recommandées

Belleflamme-Peitz, Industrial Organization

Ects : 6

Enseignant responsable :
LOUIS BERTUCCI

Volume horaire : 36

Description du contenu de l'enseignement :

While this is a fairly recent technology, this class will take students through the fundamentals of blockchains as well as implications regarding financial, economic or social interactions. The class will start by some history needed to understand what lead to the creation of Bitcoin, the first blockchain, in 2009. We will then review the detailed functioning of a blockchain. We will continue by discussing important current developments in the industry as well as implications for the economic environment. Lastly, we will discuss potential future developments and how blockchains will impact a broad range of industries. Students will also be introduced to recent academic work related to blockchains.

Students will be asked to pick a blockchain project from a list and present it briefly during the presentation session in front of the class (group presentation). When reaching this presentation session, students will be expected to be able to assess the pros and cons of a given blockchain project, and have a critical opinion on this project.

Coefficient : 2

Pré-requis recommandés :

The first prerequisite is coding. Knowledge in Python and/or Javascript will greatly help students perform the homework. Student less familiar with Python are expected to increase their Python skills by the end of the semester.

The second prerequisite is basic economics (competition, market economy, utility maximization).

While knowledge in computer science and economics is needed to properly understand what a blockchain is, we will go through what is needed just to make sure everyone is on the same page. In particular we will go through asymmetric cryptography, distributed networks, consensus, game theory, financial markets and corporate finance. Although students with knowledge in any of those topics will be more confortable, I intend to present them “from scratch”.

Compétences à acquérir :

The objective of this class is to give students a deep theoretical overview of what a blockchain is. Nonetheless we will also use mock-blockchains, write smart contracts and interact with them, through some computer sessions. This will help solidify the knowledge learned and de-mystify the functioning of a blockchain.

Students will gain a deep knowledge of how a blockchain works internally. They will also be very aware of the different issues and perhaps they will be able to spot new use cases for a blockchain.

Mode de contrôle des connaissances :

The evaluation is composed of a group presentation (1/3), homework (1/3) and a final exam (1/3). Class participation can be highly rewarded especially for students who struggle with homework. Students are encouraged to actively interact during the class.

Bibliographie-lectures recommandées

Melanie Swan, Blockchain: Blueprint for a new economy, O’Reilly, 2015

Andreas Antonopoulos, Mastering Bitcoin, 2nd edition, O’Reilly, 2017

Andreas Antonopoulos / Gavin Wood, Mastering Ethereum, 1st edition, O’Reilly, 2018

Primavera De Filippi/ Aaron Wright, Blockchain and the Law: The Rule of Code, Harvard University Press, 2018

Ects : 3

Enseignant responsable :
FLORENCE G SELL

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
SYLVAIN BENOIT

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
MADALINA OLTEANU

Volume horaire : 24

Description du contenu de l'enseignement :

This lecture is thought as an introduction to the analysis of complex data, and particularly to that

having a temporal component. Methods aimed at exploring and modelling time series, longitudinal data

and graphs with temporal components will be addressed. The issues of detecting patterns, breakpoints, changes of regimes, and

anomalies will be at the core of the different approaches.

 

The first chapters will be devoted to hidden Markov models. After having briefly recalled some definitions

and properties of Markov processes, we will define hidden Markov processes, illustrate them with several

examples and give some of their properties. Inference techniques using the EM algorithm and Bayesian

approaches will be presented and illustrated in practice. We will particularly focus on some specific

models which are extremely useful for segmenting time series stemming from the economics field, such as

autoregressive Markov switching models.

 

The second part of the lecture will tackle the issue of change-point detection methods. We will start

by introducing the change-point detection issue. More specifically, we will consider several frameworks and derive inference

procedures for computing and locating change-points : online vs. offline strategies, single vs. multiple

change point detection, known vs. unknown number of change points, parametric vs. non-parametric

approaches.

 

The third chapter will be aimed at introducing the issue of anomaly detection in the context of temporal

data. After having defined what an anomaly is, we will start by assessing whether and how hidden-Markov

models and change-point analysis may be useful for detecting anomalies. Then, we will compare these

two approaches with other techniques, stemming either from the field of computational statistics, or from

that of machine learning. During this chapter, we will also co nsider the questions of detecting patterns

and clustering temporal data.

 

The fourth chapter will address data that can be modelled as a graph or a temporal graph. We will start

by introduce some definitions and summaries for characterising the network (degree distribution, centrality

indices, ...). Afterwards, we will tackle the questions of community detection and graph clustering.

Eventually, we will address the issues of random networks and associated tests for randomness.

Models and methods introduced in this lecture will be practiced using existing implementations in R and

“real-life” datasets.

Coefficient : 1

Pré-requis obligatoire :

Students are expected to have some notions of probabilities, statistical inference theory and time series analysis (ARIMA models). An intermediate

knowledge of R and/or Python is also desirable.

Compétences à acquérir :

Gain some background and perspective of time series analysis from a data science point of view.

Be able to handle temporal data subject to anomalies and change-points.

Have some basic knowledge about graphs and temporal graphs mining.

Mode de contrôle des connaissances :

Data challenge. A project to be done individually or by two, analysing real life data.

Ects : 3

Enseignant responsable :
MARIE BRIERE

Volume horaire : 24

Description du contenu de l'enseignement :

The objective of the course is to discuss the impact of the introduction of robo advice on individuals’ investment decisions and the recent developments in household finance (life-cycle portfolio choices and behavioural biases).

After having attended the classes, the students will:

- Understand the main determinants of individuals’ portfolio choices and the underlying life-cycle theory

- Have a good understanding of the services offered by robo advisors and their impact on individuals’ investment behaviour

Coefficient : 1

Pré-requis recommandés :

Standard finance course (portfolio choice)

Compétences à acquérir :

Robo-advisors became increasingly popular as investors are seeking low-cost and automated investment advice. By providing personalized investment portfolios depending on individual’s profile in a flexible way and at a low cost, they start to gradually replace or complement the services traditionally offered by human advisors in the banks. The objective of this course is to discuss the services offered by robo-advisors, their role in the financial industry, but also the issues and challenges they are facing. The course will present the theory of individuals’ optimal life-cycle portfolio choices, and the traditional behavioural biases of individuals making investment decisions. We will see how automated advice can improve the services offered by human advisors by rationalizing investment decisions and customizing the advice to each individual’s needs. Finally, we will discuss their impact on individuals’ behaviour by analysing the results of most recent academic research on the topic.

Mode de contrôle des connaissances :

Final Exam/Project

Bibliographie-lectures recommandées

Barber, B. M. and Odean, T. (2013), The behavior of individual investors, in Handbook of the Economics of Finance, Elsevier, 1533-1570

Beshears, J. and Choi, J.J. and Laibson, D. and Madrian, B.C. (2018), “Behavioral Household Finance”, NBER Working Paper No. w24854.

Campbell, J. Y. (2006), “Household Finance”, Journal of Finance, 61(4), 1553-1604.

Cocco, J. F., Gomes, F. J., & Maenhout, P. J. (2005). Consumption and portfolio choice over the life cycle. Review of Financial Studies, 18(2), 491-533.

D’Acunto, F. Prabhala, N. and Rossi, A. (2019), “The Promises and Pitfalls of Robo-advising” - Review of Financial Studies, 32(5), 1983–2020.

Gargano, A. and Rossi A.G. (2018). "Does it Pay to Pay Attention?", Review of Financial Studies 31(12), 4595- 4649.

Guiso, L. and Sodini, P. (2012), Household Finance: An emerging field, Discussion Paper.

Merton, R. C. (1969), ‘‘Lifetime Portfolio Selection Under Uncertainty: The Continuous-Time Case,’’ Review of Economics and Statistics, 51, 247–257.

Merton, R. C. (1971), ‘‘Optimum Consumption and Portfolio Rules in a Continuous-Time Model,’’ Journal of Economic Theory, 3, 373–413.

Ects : 3

Enseignant responsable :
RENE AID

Volume horaire : 24

Description du contenu de l'enseignement :

The lecture is a sequence of use-cases in the industry and in the service business performed by professionals.

Coefficient : 1

Compétences à acquérir :

Knowing some of the most common use cases of data sciences in firms decision making business.

Mode de contrôle des connaissances :

Presentation of a resume of the lectures before a jury.

Ects : 3

Enseignant responsable :
BASTIEN BALDACCI

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
PAUL VALENTIN NGOBO

Volume horaire : 24

Coefficient : 1

Ects : 3

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
MATHILDE GODARD

Volume horaire : 24

Description du contenu de l'enseignement :

A wide variety of innovations, ranging from the use of artificial intelligence to shared medical records, through the construction of data platforms (e.g. Health Data Hub), the matching of health data to socio-economic administrative data (e.g. EDP-Santé) or the introduction of medical diagnostic instruments in socio-economic surveys (serological measurements in Epicov; blood samples in Constances, tool for measuring HCAP cognitive impairment in SHARE), renew the health data available to social science researchers, but also the way they process it.

The course will consist of three parts. In a first part, we will take stock of “standard” health data (survey data, administrative data), and then discuss the “new” sources of health data (connected objects, Doctolib, location of health professionals via OpenStreetMap). etc.). How do we access these data, and what questions do they allow us to answer?

The second part will be essentially methodological, and will seek to understand how machine learning can be complementary to public policy evaluation methods traditionally used in economics.

The third part will seek to identify new applications in social sciences, and in economics in particular: beyond the applications identified in pharmacovigilance (Morel et al., 2018), in targeting populations at risk (Razavian et al., 2016), in optimizing care pathways, in diagnostic aid (Horng et al., 2017), what are the new applications of big data in health in social sciences, and in economics in particular? Can these applications help improve the health of the population, reduce socio-economic inequalities in health, and make the health system more efficient? We will also discuss algorithm aversion, and the factors determining algorithm adoption by health professionals and patients.

Coefficient : 3 ECTS

Pré-requis recommandés :

Python.

Pré-requis obligatoire :

Machine Learning, Microeconometrics, R.

Compétences à acquérir :

1. Machine Learning (ML) as a part of the econometric toolbox. As applied economists, what tools, for what problems? Survey of applications in the existing literature.

2. Health data : take stock of "old" and "new" sources of data + practical hand-on sessions.

Mode de contrôle des connaissances :

In class pair-wise presentation of a research paper ; Data challenge using publicly available health data.

Bibliographie-lectures recommandées

[To be updated]

- Sendhil Mullainathan and Jann Spiess (2016) : « Machine Learning: An Applied Econometric Approach », Journal of Economic Perspectives—Volume 31, Number 2—Spring 2017—Pages 87–106

- Z. Obermeyer, E. J. Emanuel (2016) : « Predicting the Future — Big Data, Machine Learning, and Clinical Medicine », N. Engl. J. Med. 375, 1216–1219.

- Stefan Wager & Susan Athey (2018) « Estimation and Inference of Heterogeneous Treatment Effects using Random Forests », Journal of the American Statistical Association, 113:523, 1228-1242, DOI: 10.1080/01621459.2017.1319839

- Jon Kleinberg, Himabindu Lakkaraju, Jure Leskovec, Jens Ludwig and Sendhil Mullainathan (2017) : « Human decisions and machine predictions », NBER WP 23180.

Ects : 9

Description du contenu de l'enseignement :

Students must intern at a company (semester 4) for at least 4 months.

Coefficient : 3

Compétences à acquérir :

The students should also complete an end-of-studies internship lasting at least 4 months. The curriculum includes guest lectures by visiting professionals on issues related to Big Data, providing another means of connecting with relevant business circles.

Mode de contrôle des connaissances :

The internship will conclude with a report to be reviewed by a committee.

Ects : 3

Enseignant responsable :
MATTHIJS DEN BESTEN

Volume horaire : 10

Coefficient : 1

Ects : 3

Enseignant responsable :
Pierre SENELLART

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
JEROME LANG

Volume horaire : 24

Coefficient : 1

Ects : 3

Enseignant responsable :
MOHAMMED RIDA LARAKI

Volume horaire : 24

Coefficient : 1