Diploma in Time Series Models for Engineering (ARIMA→DL)
Online postgraduate diploma of 800 hours in time series models for engineering, from ARIMA to deep learning. 8 modules covering ARIMA and state-space models, machine learning for time series, recurrent and convolutional networks, transformers and foundation models, and forecast deployment, with an assigned technical tutor.
Diploma in Time Series Models for Engineering (ARIMA→DL) — studying from Singapore
Singapore has invested heavily in artificial intelligence and data, under national plans coordinated by the Infocomm Media Development Authority and the AI Singapore programme. The sector spans industrial analytics, digital twins, simulation for engineering design and data platforms serving finance, logistics and healthcare. Engineers work across machine learning, data engineering and computational modelling. Employers range from global technology firms and banks to local research institutes and government-linked companies.
Fees for Singapore: S$2,560 (Singapore dollar), with instalments and employer sponsorship available.
Relevant bodies in Singapore
Typical roles
Questions from Singapore
Does Singapore have a recognised body for data and AI professionals, and is SEIUM recognised?
Singapore's Infocomm Media Development Authority (IMDA) and the Singapore Computer Society are key bodies in the digital and data field, and the Personal Data Protection Commission (PDPC) oversees data protection. SEIUM's qualifications are private, not state degrees, and not accredited by any national body. Acceptance is decided by employers or the relevant body, so verify this before enrolling.
Which Singapore employers hire data, AI and simulation specialists?
Demand is strong across banks, government agencies, healthcare, logistics, telecoms and tech firms. Singapore's national AI and smart nation initiatives also create roles. Employers typically assess portfolios, technical interviews and proven projects. Your final project can demonstrate applied analytics or simulation skills, though hiring decisions are the employer's.
Can I study this part-time from Singapore, and does it need a student visa?
Yes, the programmes are 100% online and taught in English, so you can study from Singapore without a student visa. Workload is substantial, with 1,900 hours for a master's, 800 for a postgraduate diploma and 300 for a specialist course. Fees can be paid in instalments, and employer sponsorship is possible, subject to your employer's approval.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Analyse the properties of engineering time series.
Model series with ARIMA, SARIMA and exogenous variables.
Apply exponential smoothing and state-space models.
Develop multi-step forecasts with machine learning.
Train recurrent and temporal convolutional neural networks.
Evaluate transformers and foundation models against simple baselines.
Deploy and monitor forecasting models in production.
Who it's for
- Industrial data scientists working with sensor, production and consumption data.
- Forecasting engineers who need to go beyond classical statistical models.
- Energy demand analysts producing load and consumption forecasts.
- Machine learning engineers moving into temporal and sequential data.
- Process control engineers using predictions to anticipate plant behaviour.
- Planning analysts who rely on reliable demand forecasts.
- Engineering or science graduates looking to move into the energy sector.
What you'll work with
- ISO 16269-4 (statistical interpretation of data: detection of outliers)
- ISO 3534-1:2006 (statistical vocabulary)
- ISO/IEC 23053:2022 (framework for AI systems using ML)
- ISO 50006:2023 (energy performance indicators)
- ISO/IEC 25059:2023 (quality model for AI systems)
- Python with statsmodels
- Nixtla StatsForecast and NeuralForecast
- Darts
- PyTorch Forecasting
- LightGBM
8 modules
1.1Components: trend, seasonality and noise1.2Stationarity and ADF and KPSS tests1.3Autocorrelation and partial autocorrelation1.4STL seasonal decomposition1.5Irregular sampling and resampling1.6Missing values and interpolation1.7Multivariate and exogenous series1.8Time series cross-validation1.9MAE, RMSE, MAPE and MASE metrics1.10Workshop: exploratory analysis of energy consumption
2.1AR, MA and ARMA models2.2Differencing and ARIMA2.3Box-Jenkins identification2.4SARIMA for seasonality2.5Exogenous variables with ARIMAX2.6Residual diagnostics and Ljung-Box2.7Automatic selection with AIC and BIC2.8Prediction intervals2.9Limitations of linear models2.10Practical exercise: SARIMA for a plant's demand
3.1Simple and Holt exponential smoothing3.2Additive and multiplicative Holt-Winters3.3ETS models of error, trend and seasonality3.4State-space formulation3.5Kalman filter3.6Structural time series models3.7GARCH volatility models3.8Hierarchical forecasting and reconciliation3.9Prophet and its assumptions3.10Lab: Kalman filter for a noisy sensor
4.1Lag and window feature engineering4.2Gradient boosting with LightGBM4.3Multi-step forecasting strategies4.4Global versus local models4.5Calendar and event variables4.6Probabilistic forecasting with quantiles4.7Selection of temporal features4.8Information leakage4.9Comparison with statistical models4.10Practical exercise: multi-step forecasting with LightGBM
5.1LSTM and GRU networks5.2Seq2seq encoder-decoder architectures5.3Causal convolutions and TCN5.4Probabilistic DeepAR model5.5N-BEATS and N-HiTS5.6Normalisation and scaling of series5.7Regularisation and early stopping5.8GPU training5.9Interpretability of temporal networks5.10Lab: TCN for thermal load forecasting
6.1Attention applied to time series6.2Temporal Fusion Transformer6.3Informer, Autoformer and PatchTST6.4Foundation models: TimeGPT, Chronos and Moirai6.5Zero-shot forecasting6.6Fine-tuning with plant data6.7When simple models win6.8Computational cost of training6.9Rigorous evaluation with benchmarks6.10Case study: comparison of ARIMA, LightGBM and PatchTST
7.1Forecasting pipelines in production7.2Periodic model retraining7.3Continuous backtesting in production7.4Monitoring forecast error7.5Forecasting at the edge7.6Integration with planning and control7.7Communicating uncertainty7.8Governance and documentation7.9Model selection according to the case7.10Workshop: forecasting pipeline with backtesting
8.1Engineering problem and data8.2Exploratory analysis for the forecast8.3Statistical baseline models8.4Machine learning models8.5Deep learning models8.6Comparative evaluation of the forecast8.7Deployment proposal8.8Technical conclusions of the forecast8.9Report and presentation8.10Final project: final review with the tutor
How you'll learn
Training is 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so the programme fits around your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python with statsmodels, Nixtla StatsForecast and NeuralForecast, Darts, PyTorch Forecasting and LightGBM, in free, academic or evaluation versions. Exercises are based on real procedures: backtesting forecasting models with temporal validation, comparing statistical and deep models, and probabilistic forecasting of energy demand. Assessment is continuous by module, plus the final capstone project.
Standards covered: ISO 16269-4, ISO 3534-1:2006, ISO/IEC 23053:2022, ISO 50006:2023, ISO/IEC 25059:2023.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- An internet connection and a computer capable of running the programme software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Python with statsmodels, Nixtla StatsForecast and NeuralForecast, Darts, PyTorch Forecasting and LightGBM, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
Prior technical training or professional experience in the sector; no university degree is required.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Diploma in Reliability Metrics and Controlled Trials
Online postgraduate diploma of 800 hours in dependability metrics and controlled testing: 8 modules covering reliability and its measures, statistical life analysis, system reliability, design of…
Diploma in Model Compression and Inference in MCU/NPUs
Online postgraduate diploma of 800 hours in model compression and inference on MCUs/NPUs. 8 modules covering edge inference hardware, efficient architectures, quantisation, pruning and distillation, compilers…
Diploma in Electrical Asset Twins and DERMs
Online postgraduate diploma of 800 hours in electrical asset digital twins and DERMS: 8 modules covering grid assets, asset modelling with CIM (IEC 61970/61968), asset digital…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships