Accelerating AI Adoption during the pandemic

Retail Case Study:
Demand Forecasting & Price Optimisation

CUSTOMER BACKGROUND AND GOALS

The Client, one of the world’s largest global apparel brands, has embarked on a mission of becoming a “digital apparel company”, staying at the forefront of AI innovation to optimise its processes and improve customer experience.

Since the onset of the pandemic, the client has been focusing on better understanding the fast-evolving consumer behaviour and the market dynamics leveraging predictive analytics, big data, AI, Machine Learning (ML). They wanted to utilise new external data sources such as Covid parameters, macroeconomic indicators, mobility data, social distancing regulation and tourism data in order to revamp their Merchandising Planning Process- to enable faster and more accurate data driven decision.

Deploying predictive analytics at scale required a modern AI-enabled cloud data platform and a variety of rare skills. To address this challenge the client turned to Data Reply, a specialist in big data, data engineering and AI ML who could provide a team of specialists augmenting the client’s internal resources to deliver necessary support and accelerate time to value. 

THE ASK: RETAILER CONTROL ROOM

  • The first task for Data Scientists was to help the client with identifying key KPIs involved in driving the revenue recovery post peak pandemic across the business using ML capabilities.
  • Based on these KPIs the client wanted to create a ‘Control Room’ - a dashboard to monitor various aspects of the business performance to enable faster and better decisions around demand planning, order management and replenishment, pricing, inventory and supply chain management.


Demand Forecasting

Hear from our Data Scientist how Data Reply worked with a global apparel brand to help them gain a better understanding of changing consumer behaviours to enable a fast growth recovery during and post-pandemic leveraging external data, AI and Machine Learning.


Pricing & Promotions Optimisation

Hear from our Data Scientist how Data Reply worked with a global consumer brand to help them with Pricing Decisions - the initial price, promotions and markdowns generating increasing sell-through rate by up to 5 times.

OUR APPROACH

Two main workstreams were set up to address customer goals leveraging secure and scalable
AWS technology stack and Dataiku ML platform:
  • strip-0

    Data science & machine learning

    Amazon SageMaker and Dataiku platforms were used by Data Reply to develop machine learning models enabling AI based insights and recommendations in three key areas:
    • Demand Forecasting & Sell-through predictions
    • Pricing & Markdown Decisions
    • Inventory optimisation (intra-store transfers to minimise overstock and stock–out)

    The human feedback loop helped with model improvements, with achieving a more trusted, accepted by the business AI

  • Data engineering

    Data Reply specialists were responsible for:
    • Migrating existing databases and pipelines onto a secure, scalable AWS cloud environment ensuring compliance and standardisation across global data teams
    • Data ingestion, building ETL pipelines to facilitate domain-specific reporting on specified KPIs and generating alerts
    • Ethical scraping and collection of external data obtained from reliable third-party vendors

    strip-1

Key Data science & machine learning use cases


KEY BENEFITS

  • Increased revenues
    and margins

    Better decisions resulted in a five-fold increase in ‘sell through’ rate, as well as an increased Gross Margin in $millions in the initial 6 months pilot

  • Improved productivity
    from automation

    Improved productivity from the decision automation, taking away the ‘heavy lifting’ from the client’s team allowed client’s specialists to focus on more value add, strategic activities

  • Improved business agility
    and time to market

    The AI enabled robust scalable platform improved the demand forecast capability and created a ‘smart start ‘ for adding new business cases to improve customer experience and operational efficiencies.

Collaboration with Data Reply facilitated the client’s team upskilling in AI and Machine Learning through on-job learning accelerating their AI adoption and time to business value.

HOW DATA REPLY CAN HELP?

Not sure how to start using AI and machine learning for Demand Forecasting?
Check out our Proof of Value /POC offer - a time-boxed (4-5 weeks), fixed price engagement:


Do you have challenges in deploying your ML models in production, with operationalisation and scaling?
We can help with productionisation or check out our MLOPs Capability Assessment Consulting offer:

Before filling out the registration form, please read the Privacy notice pursuant to Article 13 of EU Regulation 2016/679
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input

Privacy

I declare that I have read and fully understood the Privacy Notice and I hereby express my consent to the processing of my personal data by Reply SpA for marketing purposes, in particular to receive promotional and commercial communications or information regarding company events or webinars, using automated contact means (e.g. SMS, MMS, fax, email and web applications) or traditional methods (e.g. phone calls and paper mail).
  • strip-0

    DATA REPLY

    Data Reply is the Reply group company offering a broad range of advanced analytics and AI-powered data services. We operate across different industries and business functions, enabling them to achieve meaningful outcomes through effective use of data. We have strong competences in Big Data Engineering, Data Science and IPA; we build Big Data platforms and implement ML and AI models in a manner that is repeatable, efficient, scalable, simple and yet secure. We supports companies in combinatorial optimization processes with Quantum Computing techniques that enable an engine with high computational performances.