While working on forecasting (understand “time series analysis”) I found several interesting and state of the art articles from Rob J. Hyndman. He is the co-author, with George Athanasopoulos of Forecasting: Principles and Practice. This is an excellent concise and comprehensive text explaining concepts behind forecasting, common algorithms and how to implement them in R (for a business view of forecasting, I advise Future Ready).
The book presents key concepts of forecasting. From judgemental forecasting (which can be useful when you have no or few data) to simple/multiple regression, time series decomposition, exponential smoothing (ETS), ARIMA and a few more advanced topics such as Neural Networks. I would suggest to the author to add Support Vector Regression (SVR) and ensemble learning for the next edition of the book. Each concept of the book is covered through examples with real data. What is most appreciable about the book is how concise and readable it is. Each sentence is useful to understand the described concept, nothing superfluous.
The book contains good overview and schema about each technique and how to set their meta-parameters. The R codes are well presented, concise and easy to implement and test. The book can easily be used to teach forecasting since each chapter contains exercises. In conclusion, Forecasting: Principles and Practice is THE book to learn time series analysis algorithms and how to implement them.
“You don’t need to predict the future. Just choose a future — a good future, a useful future — and make the kind of prediction that will alter human emotions and reactions in such a way that the future you predicted will be brought about. Better to make a good future than predict a bad one.”
Isaac Asimov, Prelude to Foundation
If you like hard science fiction with… Continue reading...
This is a guest post from Ethan Millar.
Big data is the latest competitive advantage for businesses. Data are now woven into every industry and function across the global economy. The use of Big data will become the basis of competition and growth for businesses by enhancing the productivity and creating significant value for global economy with waste reduction and increased quality of products and services.
This infographic is proposed by Sandipan Pal.
Finally, the day has arrived.
After years of teaming up for group studies, setting goals and planning to fare better than your competition, you have achieved it.
Topped your grades and now waiting to make a mark in your field.
But, how do you make a mark?
Easier said than done, isn’t it?
Traditionally, it would mean… Continue reading...
Today’s guest post is written by Mohammad Farooq
If there’s one thing that businesses across all industries have in common today, it’s in their increased adoption of data to shape business decisions. Below is a demonstration of how key industries use analytics tools and the benefits these tools have in solving challenges of data capture and use to shape growth.
The Data Science Handbook gathers 25 interviews of Data Scientists. Interviews are well done, most questions depending on the previous answer. This gives a nice feeling of discussion between the interviewer and the Data Scientist. On the content side, it provides interesting insights about the job of Data Scientist. The book is however biased towards pioneers in the field spending 14h… Continue reading... | 9 Comments
Going opposite direction to the current Big Data trend, Johnson and Gluck discuss the little data we consume everyday in their book Everydata. The book is a fresh and easy reading. Through several practical examples, authors covers topics such as sample selection bias, correlation vs. causation and graphics (e g. how to play with plot axes).