𝐃𝐞𝐞𝐩 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐈𝐬 𝐖𝐡𝐚𝐭 𝐘𝐨𝐮 𝐃𝐨 𝐍𝐨𝐭 𝐍𝐞𝐞𝐝
Unless you have tons of clean data and tens of top PhDs working on forecasting for over a decade as Amazon and Alibaba do.
When it comes to time series and forecasting, “𝐃𝐞𝐞𝐩 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐈𝐬 𝐖𝐡𝐚𝐭 𝐘𝐨𝐮 𝐃𝐨 𝐍𝐨𝐭 𝐍𝐞𝐞𝐝.”
And whoever tells you that your company needs deep learning for forecasting is either unfamiliar with the subject or has vested interests in selling an ineffective piece of consulting advice or a forecasting technology that does not work.
And for your average Joe Bloggs Inc multibillion super-duper company listed on cool Nasdaq or not-so-cool NYSE stock exchange, it 𝐝𝐨𝐞𝐬 𝐧𝐨𝐭 𝐰𝐨𝐫𝐤 𝐧𝐨 𝐦𝐚𝐭𝐭𝐞𝐫 𝐰𝐡𝐚𝐭 𝐲𝐨𝐮𝐫 𝐞𝐱𝐩𝐞𝐧𝐬𝐢𝐯𝐞 𝐜𝐨𝐧𝐬𝐮𝐥𝐭𝐚𝐧𝐭𝐬 𝐨𝐫 𝐧𝐨𝐭-𝐬𝐨-eep in forecasting 𝐤𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 𝐏𝐡𝐃-𝐢𝐧-𝐢𝐫𝐫𝐞𝐥𝐞𝐯𝐚𝐧𝐭 𝐟𝐢𝐞𝐥𝐝𝐬 𝐃𝐚𝐭𝐚 𝐒𝐜𝐢𝐞𝐧𝐭𝐢𝐬𝐭 𝐭𝐞𝐥𝐥𝐬 𝐲𝐨𝐮.
Fire your expensive consultants and your PhD-in-irrelevant-field Data Scientist and save yourself a lot of time, trouble and millions in wasted costs and foregone profits. DO NOT use deep learning for forecasting unless you have tons of clean data.
” FreDo: Frequency Domain-based Long-Term Time Series Forecasting”, a new research 🧐 paper from MIT, pits super fancy transformer architecture against a simple, almost mechanical benchmark.
𝕋𝕃;𝔻ℝ 𝕋𝕣𝕒𝕟𝕗𝕠𝕣𝕞𝕖𝕣 𝕝𝕠𝕤𝕖𝕤 𝕘𝕣𝕠𝕥𝕖𝕤𝕢𝕦𝕖𝕝𝕪.
A simple, almost mechanistic benchmark forecasting model from Massachusetts Institute of Technology totally decimates sophisticated transformer-based architecture. And not one of your average transformers, the best and brightest of them transformer for time series, the one that is better than another transformer that in turn is better than another transformer and so on.
𝕐𝕖𝕤, 𝕪𝕠𝕦 𝕙𝕒𝕧𝕖 𝕙𝕖𝕒𝕣𝕕 𝕚𝕥 𝕣𝕚𝕘𝕙𝕥. 𝕊𝕚𝕞𝕡𝕝𝕖 𝕒𝕝𝕞𝕠𝕤𝕥 𝕞𝕖𝕔𝕙𝕒𝕟𝕚𝕤𝕥𝕚𝕔 𝕓𝕖𝕟𝕔𝕙𝕞𝕒𝕣𝕜 𝕕𝕖𝕔𝕚𝕞𝕒𝕥𝕖𝕤 𝕥𝕙𝕖 𝕞𝕖𝕒𝕟𝕖𝕤𝕥 𝕥𝕚𝕞𝕖 𝕤𝕖𝕣𝕚𝕖𝕤 𝕥𝕣𝕒𝕟𝕤𝕗𝕠𝕣𝕞𝕖𝕣. Like a bunch of kids in Michael Bay’s movie win vs meanest transformer 🍿
Like transformers? Stick to NLP. Transformers are excellent for 😎 NLP domain, just not that awesome for #timeseries. Not at all. Please don’t use them.
It is not all about transformers. Using deep learning for time series is not the brightest idea 💡 either. Even the most brilliant forecasting experts at Amazon Forecasting R&D fell into the trap of thinking that an average forecasting use case is amenable for deep learning. After the Kaggle Walmart forecasting competition
The reason transformers don’t work well for time series is straightforward — errors accumulate in transformer-based architectures, and there is nothing the big transformer can do about it. Not yet.
A bit of consolation for DeepAR and others is that they are now in a good company of #deeplearning models for time series that do-not work so well.
ARIMA boosted trees, …, secret sauce less known approach [hey, it’s a free Medium article did you expect freebie expert advice 🔑 ] > deep learning.
Want fast ARIMA -> use Nixtla’s super fast ARIMA. Save your computing time and costs [free unaffiliated pluggin] just because the Nixtla team now what they are doing and are fantastic. One can’t get 1 million models fitted in 20 minutes with any other ARIMA.