SoloQuant Flagship Program Early Bird · $420 USD (Save $379) · Sep 1–Dec 1, 2026 · Launch Jan 1, 2027 →

SoloQuant Academy

Short evening lessons for people who work. Quant trading, Python, data, systems, architecture.

Information Hub Student Portal Privacy Policy Terms & Conditions

Academy notes

Information Hub

Articles and updates from SoloQuant Academy.

Tag: python

pythonpapertime-seriestransformersurveyafter-work

Introducing Transformers in Time Series: A Survey for after-work quants

Wen, Zhou, Zhang, Chen, Ma, Yan and Sun (IJCAI 2023; arXiv:2202.07125) map TS Transformers by module (position, attention, hierarchy) and by task (forecast, anomaly, classify). Complexity table, ETTm2 length/depth/decomposition probes, GitHub living list. Plain-language intro. Not investment advice.

python

paper

time-series

transformer

survey

after-work

Introducing Transformers in Time Series: A Survey for after-work quants

Wen, Zhou, Zhang, Chen, Ma, Yan and Sun (IJCAI 2023; arXiv:2202.07125) survey Transformers for time series. Taxonomy: module tweaks (positional encodings, sparse/low-rank attention) vs architecture (hierarchical). Applications: forecasting, anomaly, classification. Their ETTm2 checks: longer inputs often hurt; 3–6 layers beat 48; seasonal-trend decomposition can cut MSE 50–80%. Map before you pick Informer vs PatchTST. Plain-language intro. Not investment advice.

pythonpapertime-seriesitransformerforecastingafter-work

Introducing iTransformer: Inverted Transformers Are Effective for Time Series Forecasting for after-work quants

Liu, Hu, Zhang, Wu, Wang, Ma and Long (ICLR 2024; arXiv:2310.06625) invert the Transformer: each variate’s full look-back is one token. Attention mixes assets; FFN (shared MLP) encodes that series; LayerNorm is per variate. No new attention gadget. Strong on high-dimensional ECL/Traffic/PEMS; inverting also lifts vanilla/Informer/Reformer. thuml/iTransformer. Plain-language intro. Not investment advice.

pythonpapertime-seriestimesnetforecastingafter-work

Introducing TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis for after-work quants

Wu, Hu, Liu, Zhou, Wang and Long (ICLR 2023; arXiv:2210.02186) argue 1D series hide intraperiod vs interperiod variation. FFT picks top-k periods, reshape each into a 2D tensor (columns = inside a period, rows = same phase across periods), run a shared Inception block, softmax-amplitude mix. SOTA-ish across forecasting, imputation, UEA classification, anomaly detection. thuml/TimesNet. Plain-language intro. Not investment advice.

pythonpapertime-seriestimesnetforecastingafter-work

Introducing TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis for after-work quants

pythonpapertime-seriestftforecastingafter-work

Introducing Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting for after-work quants

Lim, Arik, Loeff and Pfister (IJF 2021; arXiv:1912.09363) build TFT for multi-horizon forecasts that mix static covariates, past-observed series, and known-future inputs (calendar, promotions). GRNs + GLU skip unused parts; variable selection names which features matter; LSTM does local processing; interpretable multi-head attention does long range; quantiles 0.1/0.5/0.9. Electricity, Traffic, Favorita, volatility. Plain-language intro. Not investment advice.

pythonpapertime-seriesnhitsforecastingafter-work

Introducing N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting for after-work quants

Challu, Olivares, Oreshkin, Garza, Mergenthaler-Canseco and Dubrawski (AAAI 2023; arXiv:2201.12886) keep N-BEATS residual MLP stacks, then add MaxPool multi-rate sampling and hierarchical interpolation so each block owns a frequency band. Univariate, shared weights. About 16% MSE / 14% MAE vs Transformer LTSF baselines, about 50 times faster. NeuralForecast. Plain-language intro. Not investment advice.

pythonpapertime-seriestftforecastingafter-work

Introducing Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting for after-work quants

pythonpapertime-seriesnhitsforecastingafter-work

Introducing N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting for after-work quants

pythonpapertime-seriesmomentfoundation-modelafter-work

Introducing MOMENT: A Family of Open Time-series Foundation Models for after-work quants

Goswami, Szafer, Choudhry, Cai, Li and Dubrawski (CMU Auton Lab, ICML 2024; arXiv:2402.03885) release open TS foundation models (40M / 125M / 385M). Masked patch reconstruction on the Time Series Pile; one encoder for forecast, classify, impute, anomaly. Hugging Face AutonLab/MOMENT-1-large. Plain-language intro. Not investment advice.

pythonpapertime-seriesnbeatsforecastingafter-work

Introducing N-BEATS: Neural basis expansion analysis for interpretable time series forecasting for after-work quants

Oreshkin, Carpov, Chapados and Bengio (ICLR 2020; arXiv:1905.10437) stack fully-connected residual blocks with a forecast/backcast fork. No TS feature engineering. Generic N-BEATS beats the M4 hybrid winner by ~3% OWA; an interpretable trend+Fourier variant stays within a hair. M3 and tourism too. Plain-language intro. Not investment advice.

pythonpapertime-seriesinformertransformerafter-work

Introducing Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting for after-work quants

Zhou, Zhang, Peng, Zhang, Li, Xiong and Zhang (AAAI 2021; arXiv:2012.07436) fix three Transformer LSTF bottlenecks: quadratic attention (ProbSparse O(L log L)), stacked-layer memory (self-attention distilling), and slow step-by-step decode (one-shot generative decoder). ETT oil temperature, ECL, Weather. Plain-language intro. Not investment advice.

← Previous

Page 14 of 33