Although identifying missing values in regular time series is trivial,detecting them becomes a challenge with irregular timestamps. Toreduce the storage, our partner, Alfa Laval, uses an engineering trickto store measurements in time series databases only when their valuechanges. This solution, despite solving storage problems, can createproblems in data analysis. It also complicates the identification ofmissing values.

We address two problems: identifying hidden missing values fromirregular time series and developing effective imputation techniquesfor them. We use a rule-based approach to locate hidden missing val-ues tailored to the Alfa Laval dataset. Once we have identified the po-sition of hidden missing values, imputing them becomes the greaterchallenge, particularly when missing gaps are long. Our experimentsshow that while Linear Interpolation often outperforms LSTM andARIMA, it only creates a straight line between two points, failing tocapture the shape of the missing data. Consequently, in long-termgaps, we miss lots of informative fluctuations.

To address these limitations, we employ a pattern-based similar-ity search method, which effectively captures the value and shape oftime series data for more accurate imputation. This thesis presentsour novel approach, which we validate on a subset of Alfa Laval’ssensor data and three additional external datasets, demonstrating itsgeneralizability and effectiveness. While the rule-based identificationtechnique is particularly relevant to Alfa Laval’s data, our imputationtechnique serves as a general solution for time series imputation