Dataiku > 实例探究 > 利用数据分析进行准确预测和决策:行动案例研究

利用数据分析进行准确预测和决策:行动案例研究

Dataiku Logo
技术
  • 分析与建模 - 大数据分析
  • 分析与建模 - 数据即服务
适用行业
  • 建筑物
  • 水泥
适用功能
  • 物流运输
  • 销售与市场营销
用例
  • 需求计划与预测
  • 视觉质量检测
服务
  • 数据科学服务
  • 系统集成
关于客户
Action 是一家非食品折扣零售商,在欧洲 11 个国家拥有 2,300 多家商店。他们以尽可能低的价格提供广泛的产品。
挑战
Action 是一家快速增长的非食品折扣零售商,需要利用其数据进行更准确的预测和决策。
解决方案
Action 的数据分析团队与 Capgemini 和 Dataiku 合作构建了一个强大的协作数据平台。他们实施了一个数据湖来集中和规范数据访问,并使用 Dataiku 的可视化方法通过机器学习和人工智能开发预测模型。他们还解决了诸如成本高昂且复杂的流程、缺乏可见性和控制以及运营挑战等痛点。
运营影响
  • The implementation of the new data architecture and toolset has resulted in significant operational benefits for Action. The company has been able to develop more accurate forecasting models with greater speed, enabling it to make data-driven decisions rather than relying on intuition. The use of Dataiku's platform has allowed for easier cross-team collaboration, a reliable data pipeline, and a clear view on existing processes, empowering business units to operationalize the model-generated forecasts to make real-time decisions. The company has also seen the benefits of a robust AI Governance system, which has improved visibility and control over the model building, changing, realigning, and usage processes. The move toward decentralization has allowed for the growth of a community of experts and free communication across the organization.
数量效益
  • 900% improvement on forecast runtime
  • 88% accuracy on a 52-week forecast
  • Reduced the runtime of each forecast to between 6 and 9 hours

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

相关案例.

联系我们

欢迎与我们交流!
* Required
* Required
* Required
* Invalid email address
提交此表单,即表示您同意 IoT ONE 可以与您联系并分享洞察和营销信息。
不,谢谢,我不想收到来自 IoT ONE 的任何营销电子邮件。
提交

感谢您的信息!
我们会很快与你取得联系。