Improving the Accuracy and Performance of AI Models at Data Summit 2024

Time series analysis plays a crucial role in enhancing the capabilities of AI by providing valuable insights into temporal patterns, trends, and dependencies within datasets.

At Data Summit 2024, Salochina Oad, ML engineer, U.S.Xpress, Inc. held her session, “Empowering AI Through Time Series Analysis.”

The annual Data Summit conference returned to Boston, May 8-9, 2024, with pre-conference workshops on May 7.

Oad explored the synergies between time series analysis and AI, showcasing how the integration of temporal data can significantly improve the performance and accuracy of AI models.

Key points covered include temporal context in data, enhanced predictive modeling, improved anomaly detection, dynamic feature engineering, optimizing AI for time-varying data, and forecasting and trend analysis.

Data scientists are experiencing challenges in detecting and preventing fraudulent activities, she explained. This impacts the organization’s efficiency. Time series analysis will help improve informed decision-making for the future.

Time series data is comprised of the “signal” and the “noise,” she said. A typical example of this data is a weather forecast.

Other use cases include demand forecasts or sales forecasts—with questions seeking answers such as, how many orders a trucking company received this week? Or how much revenue was generated serving a specific customer?

According to Oad, the roadmap for forecasting a project includes:

  • Determining target
  • Horizon of the forecast
  • Gathering data
  • Developing a model
  • Deploying to production
  • Monitoring

The time-series pipeline consists of:

  • ETL
  • EDA
  • Preprocessing
  • Forecasting
  • Diagnostics

“We want to take data from two different dates, see if there’s a difference between these days to try and find a pattern that can help us forecast the data,” Oad said.

Many Data Summit 2024 presentations are available for review at