The Chair for Artificial Intelligence offers Bachelor and Master Theses in different Areas of Business Informatics both as in-house projects at the university and as external theses being carried out at one of our industrial partners.

As we are from Computer Science, we are mostly interested in technology supporting different kinds of business applications. This means that programming skills are required in most cases to be able to work on our topics.

In general, we have a lot of ideas and listing all of them is not feasible. So if you are interested in developing and testing methods supporting one of the application areas described below just contact us.

Internet marketing, also referred to as i-marketing, web-marketing, online-marketing, or e-Marketing, is the marketing of products or services over the Internet. Internet marketing ties together creative and technical aspects of the Internet, including: design, development, advertising, and sales. Internet marketing also refers to the placement of media along different stages of the customer engagement cycle through search engine marketing (SEM), search engine optimization (SEO), banner ads on specific websites, and Web 2.0 strategies. Topics we are especially interested in are

• Analysis of social online media: Social online networks contain information that can help to identify target groups for marketing and to analyze interests of users
• Targeted advertisement: As a result of the analysis of user interests relevant ads can be selected that are likely to catch the users interests
• Opinion mining and monitoring: People discussing their experiences in online forums provide valuable input for identifying strengths and weaknesses of a product

In cooperation with academic and industrial partners we are building systems for analyzing information in online media including user profiles in social networks, product reviews in forums and online shops as a basis for companies to better understand the needs and attitudes of their customers with respect to their products as a basis for better marketing. Thesis in this area will apply advanced methods for improving these analyses.

Current suggestions for bachelor theses (BA) and diploma theses (DA):

• (DA) Information extraction from Wikipedia and unstructured text corpora
• (DA / BA) Sentiment analysis on product reviews using networked data (NetKit)
• (DA) Sentiment analysis: recognizing sensitive content of newspaper articles or blog posts

Students interested in topics from this area should contact Cäcilia Zirn (caecilia(at)informatik.uni-mannheim.de) for further information.

Knowledge management (KM) comprises a wide range of strategies and practices to identify, create, represent, and distribute insights or experiences within an organization, as well as to enable the effective exploitation of intellectual capital. Besides the abovementioned enterprise portals KM technologies include

• Semantic technologies for searching, browsing and retrieval
• Methods for mining social media (such as bookmarks, blogs, or wikis)
• Tools to enable the efficient transfer, capture and creation of knowledge which is embodied in individuals or embedded in organizational processes
• Techniques for extracting knowledge from existing resources such as databases, corporate document repositories, or the Web (e.g. machine learning, data mining, text analytics and information extraction)
• Context-based semantic applications for mobile devices (e.g. smartphones)

Together with academic and industrial partners we are developing, e.g., methods to facilitate the semi-automatic generation of rich domain models from textual resources. Using semantic Web technologies, we furthermore support knowledge engineers and domain experts within organizations in acquiring and representing knowledge about various domains.

Students interested in any of these topics may contact Dr. Johanna Völker (johanna(at)informatik.uni-mannheim.de) for further information.

A Decision Support System (DSS) is a class of information systems (including but not limited to computerized systems) that support business and organizational decision-making activities. A properly designed DSS is an interactive software-based system intended to help decision makers compile useful information from a combination of raw data, documents, personal knowledge, or business models to identify and solve problems and make decisions. In contrast to enterprise portals, Decision Support Systems do not only gather and aggregate Information, but also implement advanced problem solving methods such as

• Diagnosis: What is the cause of a problem that occurred (e.g. why did a project run over time ?)
• Planning: What are the right steps to solve a given problem (e.g. generating an optimal project plan)
• Scheduling: What is the right assignment of resources to solve a given problem (e.g. assignment of rooms and time slots to lectures).

We are interested in methods from Artificial Intelligence and operations research for solving such tasks in the presence of hard constraints and preferences. Theses will normally apply and eventually adapt an existing method to a concrete problem and evaluate the result.

Students interested in topics from this area should contact Mathias Niepert (mathias(at)informatik.uni-mannheim.de) for further information.

An enterprise portal, also known as an enterprise information portal (EIP) or corporate portal, is a framework for integrating information, people and processes across organizational boundaries. It provides a secure unified access point, often in the form of a web-based user interface, and is designed to aggregate and personalize information through application-specific portlets. One hallmark of enterprise portals is the de-centralized content contribution and content management, which keeps the information always updated. Important functions of a portal that need to be supported by adequate methods are:

• Federation — the integration of content provided by other portals, typically through the use of web services or similar technologies.
• Personalization — he ability to prioritize most appropriate content based on attributes of the user and metadata of the available content.
• Enterprise Search — search enterprise content using search engines

We offer thesis topics related to the themes listed above. In particular, we are building a portal for Business Informatics research and are always interested in extending this portal with new functionalities.

Students interested in topics from this area should contact Heiner Stuckenschmidt (heiner(at)informatik.uni-mannheim.de) for further information.

Enterprise Application Integration (EAI) is an integration framework composed of a collection of technologies and services which form a middleware to enable integration of systems and applications across the enterprise. Enterprise Information Integration or EII as part of interprise application integration, is a process of information integration, using data abstraction to provide a single interface (known as uniform data access) for viewing all the data within an organization, and a single set of structures and naming conventions (known as uniform information representation) to represent this data; the goal of EII is to get a large set of heterogeneous data sources to appear to a user or system as a single, homogeneous data source.

We are interested in technical aspects of EII such as

• Data integration - combining data residing in different sources and providing users with a unified view of these data, i.e.
• Schema/Ontology Matching - determine semantically equivalent combinations of elements in database schemas or ontologies.
• Object Reconciliation - Identify representations of the same real world object in different information sources to avoid redundancy

In particular, we look at combinations of automatic methods for schema matching and object reconciliation on the one hand and user interaction on the other hand to provide robust and usabale solution for the integration problem.

In cooperation with indistrial partners like Ontoprise and Seeburger we offer theoretical and practical thesis topics in this areas.

Interested students should contact Christian Meilicke and Jan Nößner for more information.

Suggestions for concrete topics of a bachelor or diploma-thesis in this area:

• Analysis of efficient algorithms for matching large scale ontologies (contact Christian Meilicke)

In addition to the topics mentioned above there are also topics available that are not related to one of the areas described above.

• Developing an AI for a card or board-game (must have visisted Künstliche Intelligenz I, contact Christian Meilicke).
• Correcting semantic Rules in Cooperation with ontoprise (ontoprise is a leading company in semantic web technologies, thesis can be written in German, contact Jan Noessner).

Aside from these suggestions, always feel free to contact us with your own ideas!