7 papers
Beyond Accuracy: A Stability-Aware Metric for Multi-Horizon Forecasting
Chutian Ma, Grigorii Pomazkin, Giacinto Paolo Saggese +1
Traditional time series forecasting methods optimize for accuracy alone. This objective neglects temporal consistency, in other words, how consistently a model predicts the same fu…
DMCD: Semantic-Statistical Framework for Causal Discovery
Samarth KaPatel, Sofia Nikiforova, Giacinto Paolo Saggese +1
We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on…
A Benchmark of Causal vs. Correlation AI for Predictive Maintenance
Shaunak Dhande, Chutian Ma, Giacinto Paolo Saggese +2
Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly…
Causify DataFlow: A Framework For High-performance Machine Learning Stream Computing
Giacinto Paolo Saggese, Paul Smith
We present DataFlow, a computational framework for building, testing, and deploying high-performance machine learning systems on unbounded time-series data. Traditional data scienc…
Causal Inference in Energy Demand Prediction
Chutian Ma, Grigorii Pomazkin, Giacinto Paolo Saggese +1
Energy demand prediction is critical for grid operators, industrial energy consumers, and service providers. Energy demand is influenced by multiple factors, including weather cond…
Runnable Directories: The Solution to the Monorepo vs. Multi-repo Debate
Shayan Ghasemnezhad, Samarth KaPatel, Sofia Nikiforova +3
Modern software systems increasingly strain traditional codebase organization strategies. Monorepos offer consistency but often suffer from scalability issues and tooling complexit…