Témata prací (Výběr práce)Témata prací (Výběr práce)(verze: 336)
Detail práce
   Přihlásit přes CAS
Innovation Indicator Analysis in the European Union: A Machine Learning Approach
Název práce v češtině: Analýza inovačních indikátorů v Evropské unii s pomocí strojového učení
Název v anglickém jazyce: Innovation Indicator Analysis in the European Union: A Machine Learning Approach
Akademický rok vypsání: 2017/2018
Typ práce: bakalářská práce
Jazyk práce: angličtina
Ústav: Institut ekonomických studií (23-IES)
Vedoucí / školitel: Petr Pleticha, M.Sc.
Řešitel: skrytý - zadáno vedoucím/školitelem
Datum přihlášení: 07.06.2018
Datum zadání: 07.06.2018
Datum a čas obhajoby: 11.06.2019 09:00
Místo konání obhajoby: Opletalova - Opletalova 26, O206, Opletalova - místn. č. 206
Datum odevzdání elektronické podoby:09.05.2019
Datum proběhlé obhajoby: 11.06.2019
Oponenti: Ing. Vilém Semerák, M.A., Ph.D.
 
 
 
Kontrola URKUND:
Seznam odborné literatury
Edquist, C., Zabala-Iturriagagoitia, J. M., Barbero, J., & Zofío, J. L. (2018). On the meaning of innovation performance: Is the synthetic indicator of the Innovation Union Scoreboard flawed? Research Evaluation, 27(3), 196–211.

European Innovation Scoreboard 2018. (2018). European Commission.

Griliches, Z. (1979). Issues in assessing the contribution of research and development to productivity growth. Bell Journal of
Economics, 10(1), 92–116.

Hall, B. H. (2011). Innovation and productivity. National Bureau of Economic Research.

Schibany, A., & Streicher, G. (2008). The European Innovation Scoreboard: drowning by numbers? Science and Public Policy, 35(10), 717–732.
Předběžná náplň práce v anglickém jazyce
Topic specification
Innovations are an important determinant of economic growth. But what is innovation? What does the term “innovation” mean? How can we measure innovation? In the European Union, researchers from the Joint Research Centre attempt to answer these questions. They annually publish a report called the European Innovation Scoreboard (EIS). The EIS report summarizes innovation performance in the EU during the previous year. Even though the EIS provides a thorough analysis in a related field, it offers many opportunities for further research. The purpose of this thesis would be to extend the analysis presented by the European Innovation Scoreboard 2018.

Research areas
i. Clustering
One of the frequently mentioned components of the EIS is a composite indicator called the Summary Innovation Index. The SII score allows the innovation performance of individual EU Member States to be compared using a single number. The usage of such an approach and the construction of the SII itself is often questioned by researchers. Schibany & Streicher (2008) discuss the strengths and weaknesses of the EIS and provide a review of the selected indicators. Another study from Edquist et al. (2018) critically asses the meaningfulness of the SII under its construction and provides an alternative indicator to describe innovation performance. I would like to use hierarchical clustering to construct an alternative partition of the EU Member States and challenge the status quo.
ii. Regression
With regression analysis, I want to study the impacts of innovation on labour productivity with the usage of EIS indicators. Previous research by Griliches (1979) suggests a significant and positive impact of innovations on productivity, these findings had subsequently become established. More recent evidence (Hall, 2011) also study the relationship between innovation and productivity and affirms the previous findings. In my thesis, I would like to verify these findings on the most recent data using the EIS indicators as dependent variables. Thus, I would be able to conclude which indicators support the positive impact of innovations on productivity.

Methodology
In my thesis, I will use mostly machine learning techniques, from both unsupervised and supervised learning. From clustering techniques, an agglomerative hierarchical clustering will be applied on the dataset published together with the European Innovation Scoreboard 2018.
In the regression part, I will use panel data methods to estimate impacts of innovations on productivity. Additionally, I would like to introduce a penalized regression technique, particularly the lasso estimation to perform a variable selection. Such selection should stress out the most relevant indicators from the EIS in the context of productivity.

Outline
Abstract
1. Introduction
2. Literature Review
3. Methodology
4. Data description
5. Empirical Model
6. Conclusion
7. Bibliography
 
Univerzita Karlova | Informační systém UK