Zaman Serisi Analizi Jobs

I’m expanding our team with an AI engineer who can take the lead on end-to-end Machine Learning work. The immediate focus is on time-series data: everything from cleaning raw feeds through to building and shipping a production-ready predictive model. You’ll be working in Python (think pandas, NumPy, scikit-learn, TensorFlow or PyTorch) and will have the freedom to introduce the tools you’re most comfortable with, as long as the final stack is reproducible and easy to maintain. Here’s what I need from you: • Prepare and engineer the time-series dataset so that it’s model-ready, documenting every transformation. • Design, train, and iterate on forecasting or anomaly-detection models that outperform a naive baseline. • Hand over clean, well-comme...

• Description We have input data which is the wind speed and direction. The data consists of Recent History (input) Internal (output) Forecast (only use the regular-lat-lon-simple-level) to forecast the future: We will give you the links. Your desktop app, will use the recent history to train the model with the internal output. In realtime, your app will also read the latest file from U and V 10m to produce the latest forecast. The forecast is run every hour and will be saved into our database. We will give you the REST api to save your data. We will also need you to create a script to backtest the model. i.e. using the actual data of Jan to Dec 2024 to forecast the data of Jan 2025. The window can slide so Feb to Jan 2025 to forecast the data of Feb 2025 etc. We will also need ...

I have a set of time-stamped observations and I need a robust machine-learning solution that can forecast future values with solid accuracy. The end goal is an automated prediction/forecasting model that I can retrain as new data arrives and easily integrate into a larger Python pipeline. Here’s what I need from you: • Exploratory analysis of the raw time-series data, spotting seasonality, trends, and anomalies. • Thoughtful feature engineering (lags, rolling stats, calendar effects, exogenous variables if useful). • Model selection and training – I’m open to traditional approaches such as ARIMA/Prophet as well as more advanced architectures like Gradient Boosting or LSTM; choose what performs best and explain why. • Rigorous evaluation on a ho...