PhD Studentship - Can Neuro-linguistic Programming Applied to Printed UK News Media Outperform the Widely used Survey-based Indicator of Consumer Confidence?

Opens: Now

Funding details: Fully-funded scholarship for 3 years covers all university tuition fees (at UK level) and an annual tax-free stipend. International students are also eligible to apply, but they will need to find other funding sources to cover the difference between the home and international tuition fees. Exceptional international candidates may be provided funding for this difference. 

Number of places: 1

Number of places extra: There will be a shortlisting and interview process.

RCUK eligibility: No

Eligibility:

• A strong performance at master’s level where Economics, Statistics or Computer Science are the primary focus, with the expected completion date of the master’s degree no later than September 2024, along with at least 2.1 performance, or the equivalent, in a relevant undergraduate degree with a strong focus on Economics.
• An aptitude for coding and an interest in natural language processing, high-dimensional estimation, and computational methods.
• Previous knowledge of programming in Python is desirable for this project but not essential.
• A demonstrable aptitude to undertake research and develop into an independent researcher.
• Other relevant experience or skills will also be considered so please highlight these in your application.

Eligibility criteria will be tested both through CV screening and interview.

Study modes eligibility: Full-time

Project Details: Consumer confidence indicators (CCIs) gauge expectations about future economic developments influencing household spending and saving decisions. However, these indicators are based on surveys that have several limitations: small sample sizes (2,000 monthly in the case of the UK survey conducted by market research company GfK) with questionable representativeness and high costs. Moreover, the publication lags reduce their value during crises or as economic activity approaches turning points in the cycle.

The PhD project will see the appointed student work with the supervisory team to create a more representative and cost-effective alternative to the UK-CCI by applying machine learning and NLP techniques to articles published in leading UK newspapers.

The linguistic analysis of text in Economics and Finance has become very popular in the last few years. However, there are many challenges when modelling text data (e.g. cleaning text, variable shrinkage, interpretation of results). An important contribution of this project is to focus on the interpretation of words and the associated human emotions. Rigorous econometric methods will be used. The student will specifically evaluate the text based CCI’s responsiveness to key UK economic, financial, and political events and its performance in forecasting. In the second stage of the project daily and weekly text-based real time indicators will be created and used in nowcasting macroeconomic indicators including GDP, inflation, and the unemployment rate – this is not possible with the current low frequency and slow release of CCI data.

Primary Supervisor: Dr. Luigi Gifuni.

Additional Supervisor/s: Prof Julia Darby and Prof Dimitris Korobilis.

Contact Details: [email protected]