Détails de l'annonce
Référence:
39353
Publiée le:
2 décembre 2016
Type de poste:
Stage/PFE
Lieu de travail:
La Goulette, Tunis, Tunisie
Expérience:
Aucune expérience
Étude:
Bac + 4
Disponibilité:
Plein temps
Langues:
Français , Anglais
Mobilité:
Locale
OVH Tunisie logo
OVH Tunisie   |   Tunis
Entreprise:
MASS ANALYTICS
Secteur: consulting / étude / stratégie
Taille: Moins de 20 employés
Description de l'annonce:

 

  • About MASS-Analytics

Mass (www.mass-analytics.com) specialises in collecting and analysing big data using the latest technology available to assist companies in their strategic decision making.

MASS offers two types of services:

* Marketing Mix Modelling: We help companies understand and evaluate the performance of their marketing mix and measure the return on investment (ROI) from each media channel used and each marketing activity run. The Evaluation phase is then followed by clear recommendations on how best to optimise budgets going forward.

* Tools Development: We use the latest technology available to develop smart and integrated tools that specialise in organising, querying, charting and analysing several streams of data. Our core product “Modelling MassTer” takes the user through an end to end analysis journey from data loading, to data processing, charting, modelling, optimisation, forecasting and reporting. 

  • Graduation Internship Projects:

MASS has four potential projects offering a fantastic opportunity for a technically proficient Java Developer and/or a Data Scientist with a strong mathematical modelling skills. The candidate will help build new and maintain existing software components. The position will require supporting all phases of the product lifecycle including analysis, development and testing. World class standards are to be applied and consequently a high level of commitment is expected.

The successful candidate will have a good degree in Computer Science, Electrical Engineering, Data Analytics or similar. A keen interest in the latest development tools and technologies as well as strong problem solving skills are also expected. Familiarity with mathematical modelling and analytics is a plus.

Project 1: Web Tracking & Digital Attribution

After the proliferation of modern online marketing channels, measuring the impact of every touch point to the final customer conversion is becoming increasingly critical to the decision makers. For this reason, digital attribution is emerging as a requirement to allow marketing managers optimise the budget allocated to the various digital channels available.

In this project the candidate will have to study and implement the different attribution algorithms used in practice and compare their performance with particular emphasis on the ones based on the new algorithmic attribution approach.  Part of the project will also including implementing web tracking tools for data collection. Familiarity with Google Analytics will be a plus.

Project 2: Model Selection & Genetic Algorithms

The candidate will have to develop techniques for model selection to identify the best factors to enter a linear or a non-linear model calculated using the least squares method. The candidate will have to explore the use of genetic algorithms and compare their performance with other traditional model selection approaches. Existing search engine will have to be improved by tuning control parameters and incorporate various constraints on the search space.

Project 3: Imputation Techniques for Unbalanced Datasets

Missing data or unbalanced datasets is a common problem especially when dealing with panel data needed for regional or store by store analysis. In this project the candidate will have to explore the different imputation methods reported in the literature to deal with the problem of missing data, implement them and compare their performance. 

Project 4: Web Application

The candidate will have to implement an end-to-end multi-tier application offering a dashboard for data and results visualisation as well as an interface for optimisation and forecasting tools to help marketing managers in their decision making. The application will have both a web and a mobile phone interface allowing the user to access a web service to retrieve modelling results and display them on screen using interactive charts and tables. The user should also be able to input parameters allowing him to optimise advertising budgets and predict future sales based on pre-defined scenarios. In addition to the user interface, the candidate will also have to build the backend infrastructure including the database and the web service. 

Qualifications

  •  Skills required (essential):

· Object oriented programming and familiarity with design patterns.

· Good problem solving skills.

· Capable of working independently and reliably producing high-quality work to tight deadlines.

· Ability to communicate with technical and non-technical staff in a clear and effective manner.

  • Useful additional skills:

· Java , C#, Python, R

· Swing, hibernate, Xml, JSF, PHP, SQL

· SVN, Junit, Maven

· Mathematical skills (e.g. econometric analysis, machine learning)

· Exposure to agile development practices and Test Driven Development. 

If you feel this role is a good match for your skill set then please submit your CV.