Demand forecasting is exactly how it sounds: forecasting demand. This can take many forms but the most classic example is predicting how many products will be sold by a retailer on each particular day. This forecasting is in turn used to drive business value in various ways. The most common is better inventory management, but […]
A Different Look at Intermittent Demand Forecasting Read More »
Is ChatGPT and the its family of LLMs alive? If not, will models like these someday (soon) be alive? Do we need to be afraid of them destroying our world as we know it? And regardless of whether these things are alive or not, will they be useful? Those questions are big questions right now,
To Be, or Not to Be AGI, and how do I use it? That is the question Read More »
For the last couple of years, I have spent a large portion of my life attempting to solve the unsolvable: forecasting time series to predict the future. I have personally thought myself quite clever for the various innovations I have come up with, and the thousands of users on my free and open-source AutoTS project
Winning the M6 Competition: Financial Forecasting Decision Category Read More »
I grew up in a household where the inevitability of death was a strangely common motivator. We were told, as 10 year olds, to exercise because it would help us live longer. Bad habits were frequently flagged as sources of death. Statements about our future were usually conditioned by “if you live that long.” It
On the Technical Possibility of Living Forever Read More »
One of the more exciting new features coming soon to AutoTS is the automatic detection of holidays. That’s exactly what it sounds like: figuring out when holidays are occurring and being able to generate that calendar for the future. Firstly, why is this needed? A couple of reasons. The big reason is that holidays are
Holiday Detection for Forecasting Read More »
It has been impossible in the past to get all three of the largest neural network architectures running in the same Python environment in such a way that they don’t conflict and so that they will also train on GPU. The reason I want all the libraries running in the same environment is that AutoTS
PyTorch, Tensorflow, and MXNet on GPU in the same environment and GPU vs CPU performance Read More »
Note that a variation on this article may also be posted on the Nousot blog. Time series are a string of numbers varying across time. It could be the weather, sales of tissue paper, electricity demand of a region, or countless other things. There are plenty of useful things to do with this type of
Preprocessing for Time Series Read More »
While doing some benchmarking of my AutoTS package I quickly discovered a troubling trend – my newest, fanciest, most expensive Intel i7 CPUs – an Intel 10700 and 1165G7, were performing vastly slower than their older counterparts. I wasn’t terribly surprised to see the 1165G7 having issues: Tiger Lake – a brand new architecture CPU
For loops are very convenient. With a combination of a for loop and some if-else statements you can do just about anything. There’s just one problem though, for loops are kinda slow. There are many ways to speed up the code, the best usually, in the data science world, to use vectorized NumPy or Pandas
Multiprocessing in Python for Data Science Read More »
AutoTS development has been on hold for the last three months or so. Partly that is because it finally works more or less as I originally intended. In fact, it works better than I originally intended. Still, the current development feels like a failure as I failed to use it to submit any decent models
AutoTS: Looking Forward Read More »
