Section: Research Program

Data Analytics

Data analytics refers to a set of techniques to draw conclusions through data examination. It involves data mining, statistics, and data management, and is applied to categorical and continuous data. In the Zenith team, we are interested in both of these data types. Categorical data designates a set of data that can be described as “check boxes”. It can be names, products, items, towns, etc. A common illustration is the market basket data, where each item bought by a client is recorded and the set of items is the basket. The typical data mining problems with this kind of data are:

• Frequent itemsets and association rules. In this case, the data is usually a table with a high number of rows and the data mining algorithm extracts correlations between column values. A typical example of frequent itemset from a sensor network in a smart building would say that “in 20% rooms, the door is closed, the room is empty, and lights are on.”

• Frequent sequential pattern extraction. This problem is very similar to frequent itemset discovery but considering the order between. In the smart building example, a frequent sequence could say that “in 40% of rooms, lights are on at time $i$, the room is empty at time $i+j$ and the door is closed at time $i+j+k$”.

• Clustering. The goal of clustering is to group together similar data while ensuring that dissimilar data will not be in the same cluster. In our example of smart buildings, we could find clusters of rooms, where offices will be in one category and copy machine rooms in another because of their differences (hours of people presence, number of times lights are turned on/off, etc.).

Continuous data are numeric records that can have an infinite number of values between any two values. A temperature value or a timestamp are examples of such data. They are involved in a widely used type of data known as time series: a series of values, ordered by time, and giving a measure, e.g. coming from a sensor. There is a large number of problems that can apply to this kind of data, including:

• Indexing and retrieval. The goal, here, is usually to find, given a query $q$ and a time series dataset $D$, the records of $D$ that are most similar to $q$. This may involve any transformation of $D$ by means of an index or an alternative representation for faster execution.

• Pattern and outlier detection. The discovery of recurrent patterns or atypical sub-windows in a time series has applications in finance, industrial manufacture or seismology, to name a few. It calls for techniques that avoid pairwise comparisons of all the sub-windows, which would lead to prohibitive response times.

• Clustering. The goal is the same as categorical data clustering: group similar time series and separate dissimilar ones.

One main problem in data analytics is to deal with data streams. Existing methods have been designed for very large data sets where complex algorithms from artificial intelligence were not efficient because of data size. However, we now must deal with data streams, sequences of data events arriving at high rate, where traditional data analytics techniques cannot complete in real-time, given the infinite data size. In order to extract knowledge from data streams, the data mining community has investigated approximation methods that could yield good result quality.