AI, Machine Learning, advanced analytics in the enterprise environment Part 2 (theory)

There is a lot of discussions the past years about the revolution predictive analytics will bring to the businesses. But, predictive analytics is not something new. It used to be a part of statistics! Corporations with the resources were doing it for decades. Nowadays, however, it is more accessible, due to technological advancements in the areas of computing power, software and storage, the abundance of big datasets, and advances in algorithm research. Any student can now use the cloud to perform an experiment that a few years ago would have been possible to be performed only by large corporations or government agencies.

The challenge is how can we apply advanced analytics, and AI in an enterprise environment, efficiently and effectively.

Continue reading

Advertisements

AI, Machine Learning, advanced analytics in the enterprise environment Part 1 (a personal story from the 90s)

The first time I saw predictive analytics live, in praxis, to provide useful information was in the mid-90s. As a student and aspiring engineer, I was enrolled in a Total Quality/Six Sigma class. During a field trip we visited a Japanese run, car manufacturing plant where, to my astonishment, blue-collar workers were applying regression in order to predict when to change tools!

Continue reading

Time Series Analysis Part 3 (Machine Learning)

We already have seen in the previous section how Time Series Modeling with the help of ARIMA can be realized.

In the last few years, there have been more attempts at a fresh approach to statistical time-series forecasting using the increasingly accessible tools of machine learning. This means methods like neural networks and extreme gradient boosting, as supplements or even replacements of the more traditional tools like auto-regressive integrated moving average (ARIMA) models.

Continue reading

Time Series Analysis Part 2 (ARIMA)

‘Time’ is the most important factor which ensures success in a business. It’s difficult to keep up with the pace of time.  But, technology has developed some powerful methods to enable us to ‘see things’ ahead of time.  One such method, which deals with time-based data is Time Series Modeling. As the name suggests, it involves working on time (years, days, hours, minutes) based data, to derive hidden insights to make informed decision making.

Continue reading

Time Series Analysis Part 1 (intro)

A time series is a series of data points indexed (or listed or graphed) in time order. Most commonly, a time series is a sequence taken at successive equally spaced points in time. Thus it is a sequence of discrete-time data.

Time Series Data obviously has to do with time and the first thing that comes to mind is finance. The world of finance is the world of time series, so stocks, and currency exchange rates and interest rates, they’re all Time series.

Continue reading