Cette opportunité est basée à Lausanne

Using non-financial indicators to build a Robot Advisor (Diploma Thesis/ Internship)


How to predict future market move? The objective of this internship is to develop a “robot advisor” and to compare its predictions with current market trends

Big Data allows new forms of data processing. One of the most promising attempts is the so-called Robot Advice. Robot Advice can be looked at as a functionality, which provides automated financial advice by means of applying a combination of data analysis techniques on a broad range of available information. The goal is to provide financial advice with limited or no human intervention.

The first part of this stage will be dedicated to select the index that will be used to build the robot advisor prototype. This can be a stock exchange, a market index, or even a currency. Then, based on historical data, influencing indicators should be selected, coming from social media (Twitter, facebook, other) or other brand-new fields (weather, Twit from influencers). The challenge will be also here to collect enough data to feed the prototype and to improve it based on results. ELCA will support the student to select the more realistic usecase to ensure a first prototype can be proposed.

The second part will be dedicated to the creation of the prototype. The Robot Advice Engine would extract, transform and interpret the data using specific connectors covering the multiple data sources. The derived data would then be processed using different techniques (classification, e-reputation, relationship discovery, sentiment analysis, pattern recognition, etc.). By combining the findings/results of the analysis performed, the engine would generate a prediction. The result of this prediction will then be compared to real case. Or even to human predictions.

As a conclusion, the student should propose a report, based on its results, evaluating the relevance of non-financial indicators to predict market trends. And perhaps prepare the topics for the next internships!


Use Case Example:  Weather forecast in the USA and stock exchange / Twit of Mr Trump and Chinese currency /Average temperature in North America and SMI

Challenges: creativity, big data analysis

Project applications: banking industry

What you will learn: developing your skills in machine learning.

Possible extensions (depends on advancement of the aforementioned work): mobile application add-on, integration with banking application.

In this role

In this project, the goal is to:

  • Build a robot advisor to improve self-finance management

Ce que nous proposons

Join our team as intern and you will find a young, dynamic and culturally diverse working environment.

About your profile

  • Required: machine learning and deep learning, computer vision, mobile app development
  • Software engineering: Java, deep learning libraries, mobile API (iOS, Android), python.

If you are INTERESTED in applying for this position, please send us your complete application (CV, cover letter, letter of reference, diplomas and certificates).

En continuant votre navigation sur ce site, vous acceptez l'utilisation de cookies ou technologies similaires ayant pour finalité la réalisation de statistiques de visites sur notre site (tests et mesures d'audience, de fréquentation, de navigation, de performance), mais également de vous proposer des contenus et annonces ciblés et adaptés à vos centres d'intérêt.

Nos cookies ont été mis à jour. N'hésitez pas à mettre à jour vos préférences.


Gérer vos préférences cookies

Mettre à jour vos préférences cookies

Vous pouvez vous informer sur la nature des cookies déposés, les accepter ou les refuser soit globalement pour l'ensemble du site et l'ensemble des services, soit service par service.

OK, tout accepter

Flux de visiteur

Ces cookies nous offrent un aperçu des sources de trafic et nous permettent de mieux comprendre nos visiteurs, tout en garantissant leur anonymat.

(Google Analytics et CrazyEgg)


Outils de partage

Les cookies de médias sociaux permettent de partager des contenus sur vos réseaux préférés.



Connaissance du visiteur

Ces cookies sont utilisés pour suivre les visiteurs sur les sites Internet.

Ils doivent nous permettre d’offrir à nos visiteurs identifiés davantage de contenus pertinents et ciblés (ClickDimensions) et d’afficher des publicités susceptibles d’intéresser les utilisateurs (Facebook Pixels).


Pour plus d'informations relatives à la protection de données, cliquez ici.