Optimize assortment plans with systematic testing of localized assortment strategies

Case Study

Optimize assortment plans with systematic testing of localized assortment strategies

Challenge

As more and more retailers make the transition (or try to) from a product centric assortment strategy to a more customer centric strategy, they are still faced with many issues like determining the optimal product mix and inventory size. These issues become strategically important to solve as customers are always looking for a personalized shopping experience (both online and offline); the right assortment will drive more foot falls, repeat purchases, increase sales and profitability

Striking the perfect balance with your assortments requires data and use of advanced analytics. Specifically, you need to analyze historical data and market intelligence in order to forecast trends, launch products or promotions at the right time and prevent out of stocks. All of this needs to be done with ever changing customer preferences and how the assortment relates to local factors and seasonal factors.

Approach

Convergytics deployed an end to end merchandising solution starting with category trends & forecasting to help merchant planners understand product trends, product affinities by various customer & geographical dimensions. 

 

With this as the basis, we created a framework of A/B testing to test new localized assortment strategies based on SKU rationalization to ensure maximum coverage of assortment with always customer preferences as the pivot. 

 

We have been able to create a data driven continuous improvement (test & learn cycle) framework so merchant planners can now use intelligent design to measure impact and fine tune assortment strategies.

Result

Assortment strategies recommendations have resulted in an increase in traffic (online by 18% and stores by 12%) resulting in basket size by 15% and reduction in inventory carrying costs by 10%

Increase in traffic (online and stores) by

18% & 12%

Marketing spend optimization and planning to drive brand / sales growth

Case Study

Marketing spend optimization and planning to drive brand / sales growth

Challenge

An increasingly competitive landscape with new forms of digital competition, changing demographics are presenting retail marketers with new challenges every day.

To add to the complexity, a shift in media consumption has rendered traditional marketing channels less effective in reaching broader population. While digital channels promise more personalized & real time content delivery, their return on investment at scale remains largely suspect

 

As the media choices available takes new form (including more targeted & localized offerings) and grows, an advanced analytics solution will help marketers better manage media investments to determine the optimal marketing mix to increase ROI, sustain brand growth and drive incremental sales.

Approach

For a leading national retailer Convergytics deployed an end to end marketing attribution and marketing spend optimization. The proprietary solution is based on a Bayesian hierarchical framework which mirrors how customers, brands and advertising interact in the real world.

 

The model helped in providing clarity on unanswered questions our clients was facing – they were able to get deep insights on ROI, Contribution (how they change with events, seasonality & competitive events), effectiveness of each marketing activity (time to impact and memory factors) along with optimal spend range for each activity. All of these insights helped create the right constraints for the optimization resulting in a robust marketing spend plan.

Result

An overall increase in sales by 7.4% in the Fall season; Reduction in low performing spends like Search, Inserts and reallocation to event based TV / Radio advertising were some of the key recommendations which led to higher ROI (increase in overall ROI by nearly 40%) across all marketing activities.

Increase in sales by

7.4%

Increase in overall ROI by nearly

40%

Interested in Learning More?

Machine learning solution for real time fraud detection and verification

Case Study

Machine learning solution for real time fraud detection and verification

Challenge

In an increasing online world and many devices / channels for placing an order, customer fraud is becoming the biggest reason for margin erosion. In the last two years, online order fraud is growing twice the rate of online sales and the industry average ranges from 14 – 27%.

As retailers grapple with this problem and implement varied solutions for fraud-detection and verification, the most common problem is “false positives” – orders which are not fraud but classified as fraud. This is resulting in loss of a different kind – declining customer satisfaction and increasing customer frustration; During the holiday season such scenarios will lead to a significant loss of loyal customers.

Approach

Convergytics deployed a machine learning solution built on a big data enabled data layer to enable accurate fraud detection in real time. The solution which used a combination of unsupervised, supervised and heuristic analysis increased prediction of accuracy from 82% to nearly 93%. 

 

The different levels of fraud severity have helped in implemented less intrusive tiered verification process.

Result

Our client has realized in nearly $200 Million in savings in the last holiday season and has seen an uptick in the customer satisfaction by 14%.

Savings up by

$200 Million

Uptick in the Customer Satisfaction by

14%

Interested in Learning More?

Use machine learning to enable personalized targeting for customers

Case Study

Use machine learning to enable personalized targeting for customers

Challenge

Hyper-personalization is the first among them. He demands convenience and flexibility, and he expects to order from anywhere or any channel. He needs the offer, which fits exactly with him.

Now Personalization isn’t a perk but a necessity; this is what is driving marketers to demand more from their recommendation systems. Smart marketers now expect personalization solution to solve for “What’s next” and this doesn’t always mean products but includes intelligence on individualized offer and delivered through the right channel.

 

In the example below, we helped our client create a hyper-relevance solution to not only recommend the next best product, associated product affinities and offer but also created an algorithm to optimize placement of products in the creatives for different channels.

Approach

For a leading off-price departmental store, Convergytics implemented a machine learning based recommendation engine. The recommendation engine predicted accurate recommendation on most likely products – brands – style based on customer preferences and provided insights on related product affinities to compliment the primary product and style. Additional intelligence such as personalized offers and channel created true hyper-relevance

Result

As a result of the engagement, our client saw an increase in response rates by nearly 37%; the long-term impact could be seen through increase in number of repeat customers and offer redemptions.  Today, for any event based campaign as many as 2500 different versions of DM’s are created with an average of 235 customers / creative 

Increase in response rates by nearly

37%

Interested in Learning More?

Run centralized pricing strategies with real time offer optimization

Case Study

Run centralized pricing strategies with real time offer optimization

Challenge

Retailers can feel overwhelmed as the market place is abundant with pricing products with all of them claiming to be built on AI framework. The reality is most of these solutions miss the mark and cannot mirror how customers, prices & brands interact in the market. All this leads to an inaccurate demand estimation, inaccurate price elasticity measures eventually leading to a weak pricing solution.

In the example below, we helped our client implement a centralized base price optimization (feature-based pricing for SKUs) and using that as foundation to setup store level offer & mark-down optimizations. Our client had gone through two failed implementations from other vendors and 

Approach

For a premium watch retailer, Convergytics deployed a pricing solution based on choice-based conjoint framework and surface optimization models. The custom solution developed for our client get a deep understanding of demand patterns, elasticity measures, product-price interaction effects across categories. These insights were the basis of an optimal base price and helped in defining various pricing / promotional strategies 

Result

As a result of the engagement, the retailer saw an increase in profitability by 17%. The solution simplified pricing analysis with a web-based interface that allowed users to analyze key pricing metrics and their impact in real time. Today, pricing analysts using the solution to test several “What If Scenarios” and chose the winning pricing strategy

Increase in profitability by

17%

Interested in Learning More?

Augmented intelligence to enable dynamic customer journey orchestration

Case Study

Augmented intelligence to enable dynamic customer journey orchestration

Challenge

Many retailers are zeroing in on a strategy to better understand and map how customers use multiple channels to evaluate and purchase. Every purchase journey is unique and understanding today’s winding, end-to-end shopping journey is even challenging; now if a marketer has to orchestrate a strategy to best engage a customer in the purchase journey, it becomes even more challenging

Retailers today are faced with the challenge of managing large volumes of data and create a 360 view of the customer. Lack of an integrated view is a major deterrent to help retailers understand where the customer lies in the purchase journey, what his shopping preferences and how best to engage them with personalized targeting – all these are resulting in an incoherent targeting strategy

Approach

For a leading retailer, Convergytics developed an augmented intelligence framework built on a foundation of Customer 360 to enable dynamic, real time journey orchestration. The solution enabled our client to be proactive in engaging customers and implement a real time marketing activation strategy; the solution is now central to all marketing efforts and drives accelerated conversion through personalized offers to each customer

Result

As a result of the engagement, the retailer saw an increase in sales by 23%. In addition to the incremental sales, customer targeting strategy evolved from a siloed, reactive approach to a centralized and real time targeting with ability to engage customers with personalized content (right product, right offer and right channel) 

Increase in sales by

23%

Interested in Learning More?