Quick commerce (q-commerce) is one of the fastest growing sectors in India. It provides informal employment to approximately 4,50,000 workers, and it is estimated to become a USD 200 Billion industry by 2026. A significant portion of this industry deals with perishable goods. (e.g. milk, dosa batter etc.) These are food items which are consumed relatively fresh by the consumers and therefore their order volume is high and repetitive even when the average basket size is relatively small. The fundamental challenge for the retailer is that, increasing selling price would hamper sales and would lead to unsold inventory. On the other hand setting a price less, would lead to forgoing of potential revenue. This paper attempts to propose a mathematical model which formalizes this dilemma. The problem statement is not only important for improving the unit economics of the perennially loss making quick commerce firms, but also would lead to a trickle-down effect in improving the conditions of the gig workers as observed in [4]. The sections below describe the mathematical formulation. The results from the simulation would be published in a follow-up study.
Quick response is a widely adopted strategy to mitigate overproduction in the manufacturing industry, yet recent research reveals a counter-intuitive paradox: while it reduces waste from unsold finished goods, it may incentivize firms to procure more raw materials, potentially increasing total system waste. Additionally, existing models that guide quick response strategies rely on the assumption of a known demand distribution, whereas in practice, demand patterns are often ambiguous and historical data are scarce. To address these challenges, we develop a distributionally robust optimization (DRO) framework for the quick response model that builds robust policies even with limited data. We further integrate a novel waste-to-consumption ratio constraint into this framework, empowering firms to explicitly control the environmental impact of their operations. Our numerical experiments demonstrate that policies optimized for specific demand assumptions suffer severe performance degradation under distributional shifts, whereas our data-driven DRO approach consistently delivers superior robustness. Moreover, we find that the constrained quick response model resolves the central paradox:
Industry partners provided a problem statement that involves classifying electronic waste using machine learning models that will be used by pick-and-place robots for waste segregation. This was achieved by taking common electronic waste items, such as a mouse and charger, unsoldering them, and taking pictures to create a custom dataset. Then state-of-the art YOLOv11 model was trained and run to achieve 70 mAP in real-time. Mask-RCNN model was also trained and achieved 41 mAP. The model can be integrated with pick-and-place robots to perform segregation of e-waste.
In the fast-fashion industry, overproduction and unsold inventory create significant environmental problems. Precise sales forecasts for unreleased items could drastically improve the efficiency and profits of industries. However, predicting the success of entirely new styles is difficult due to the absence of past data and ever-changing trends. Specifically, currently used deterministic models struggle with domain shifts when encountering items outside their training data. The recently proposed diffusion models address this issue using a continuous-time diffusion process. Specifically, these models enable us to predict the sales of new items, mitigating the domain shift challenges encountered by deterministic models. As a result, this paper proposes Dif4FF, a novel two-stage pipeline for New Fashion Product Performance Forecasting (NFPPF) that leverages the power of diffusion models conditioned on multimodal data related to specific clothes. Dif4FF first utilizes a multimodal score-based diffusion model to forecast multiple sales trajectories for various garments over time. The forecasts are refined using a powerful Graph Convolutional Network (GCN) architecture. By leveraging the
Retailers have significant potential to improve recommendations through strategic bundling and pricing. By taking into account different types of customers and their purchasing decisions, retailers can better accommodate customer preferences and increase revenues while reducing unsold items. We consider a retailer seeking to maximize its expected revenue by selling unique and non-replenishable items over a finite horizon. The retailer may offer each item individually or as part of a bundle. Our approach provides tractable bounds on expected revenue that are tailored to unique items and suitable for a rich class of choice models. We leverage these bounds to propose a bundling algorithm that efficiently selects bundles in a column-generation fashion. Under the multinomial logit model, our bounds are asymptotically optimal as the expected number of arrivals $λ$ grows, yielding a performance bound in $O(1/λ)$. In contrast, we show that both the static and fluid approximations are not asymptotically optimal. Moreover, we propose a greedy algorithm that allows for tractable dynamic bundling. We show through numerical experiments that third-party logistics providers (3PL) in particular ca
The Semmeldetector, is a machine learning application that utilizes object detection models to detect, classify and count baked goods in images. Our application allows commercial bakers to track unsold baked goods, which allows them to optimize production and increase resource efficiency. We compiled a dataset comprising 1151 images that distinguishes between 18 different types of baked goods to train our detection models. To facilitate model training, we used a Copy-Paste augmentation pipeline to expand our dataset. We trained the state-of-the-art object detection model YOLOv8 on our detection task. We tested the impact of different training data, model scale, and online image augmentation pipelines on model performance. Our overall best performing model, achieved an AP@0.5 of 89.1% on our test set. Based on our results, we conclude that machine learning can be a valuable tool even for unforeseen industries like bakeries, even with very limited datasets.
The fast fashion industry suffers from significant environmental impacts due to overproduction and unsold inventory. Accurately predicting sales volumes for unreleased products could significantly improve efficiency and resource utilization. However, predicting performance for entirely new items is challenging due to the lack of historical data and rapidly changing trends, and existing deterministic models often struggle with domain shifts when encountering items outside the training data distribution. The recently proposed diffusion models address this issue using a continuous-time diffusion process. This allows us to simulate how new items are adopted, reducing the impact of domain shift challenges faced by deterministic models. As a result, in this paper, we propose MDiFF: a novel two-step multimodal diffusion models-based pipeline for New Fashion Product Performance Forecasting (NFPPF). First, we use a score-based diffusion model to predict multiple future sales for different clothes over time. Then, we refine these multiple predictions with a lightweight Multi-layer Perceptron (MLP) to get the final forecast. MDiFF leverages the strengths of both architectures, resulting in th
Recurring auctions are ubiquitous for selling durable assets like artworks and homes, with follow-up auctions held for unsold items. We investigate such auctions theoretically and empirically. Theoretical analysis demonstrates that recurring auctions outperform single-round auctions when buyers face entry costs, enhancing efficiency and revenue due to sorted entry of potential buyers. Optimal reserve price sequences are characterized. Empirical findings from home foreclosure auctions in China reveal significant annual gains in efficiency (3.40 billion USD, 16.60%) and revenue (2.97 billion USD, 15.92%) using recurring auctions compared to single-round auctions. Implementing optimal reserve prices can further improve efficiency (3.35%) and revenue (3.06%).
We investigate the scenarios in which a holonomic versus a non-holonomic frame description of gravity theories are equivalent. It turns out that classically, the equivalence holds in a way that is independent of the particular dynamics and/or spacetime dimension. This includes general metric-affine dynamics. A global bundle-theoretical investigation is carried out, uncovering the equivalence principle as the culprit. The equivalence holds as long as the equivalence principle holds. This is not something to be expected when non-invertible configurations of the vielbein field are taken into account. In such case, the gauge-theoretical description of gravity unsolders from spacetime, and one has to decide if gravity is spacetime geometry or an internal gauge theory.
Being able to forecast the popularity of new garment designs is very important in an industry as fast paced as fashion, both in terms of profitability and reducing the problem of unsold inventory. Here, we attempt to address this task in order to provide informative forecasts to fashion designers within a virtual reality designer application that will allow them to fine tune their creations based on current consumer preferences within an interactive and immersive environment. To achieve this we have to deal with the following central challenges: (1) the proposed method should not hinder the creative process and thus it has to rely only on the garment's visual characteristics, (2) the new garment lacks historical data from which to extrapolate their future popularity and (3) fashion trends in general are highly dynamical. To this end, we develop a computer vision pipeline fine tuned on fashion imagery in order to extract relevant visual features along with the category and attributes of the garment. We propose a hierarchical label sharing (HLS) pipeline for automatically capturing hierarchical relations among fashion categories and attributes. Moreover, we propose MuQAR, a Multimoda
We consider the Item Pricing problem for revenue maximization in the limited supply setting, where a single seller with $n$ items caters to $m$ buyers with unknown subadditive valuation functions who arrive in a sequence. The seller sets the prices on individual items. Each buyer buys a subset of yet unsold items that maximizes her utility. Our goal is to design pricing strategies that guarantee an expected revenue that is within a small factor $α$ of the maximum possible social welfare -- an upper bound on the maximum revenue that can be generated. Most earlier work has focused on the unlimited supply setting, where selling items to some buyer does not affect their availability to the future buyers. Balcan et. al. (EC 2008) studied the limited supply setting, giving a randomized strategy that assigns a single price to all items (uniform strategy), and never changes it (static strategy), that gives an $2^{O(\sqrt{\log n \log \log n})}$-approximation, and moreover, no static uniform pricing strategy can give better than $2^{Ω(\log^{1/4} n)}$- approximation. We improve this lower bound to $2^{Ω(sqrt{\log n})}$. We consider dynamic uniform strategies, which can change the price upon t
We present the following results pertaining to Fisher's market model: -We give two natural generalizations of Fisher's market model: In model M_1, sellers can declare an upper bound on the money they wish to earn (and take back their unsold good), and in model M_2, buyers can declare an upper bound on the amount to utility they wish to derive (and take back the unused part of their money). -We derive convex programs for the linear case of these two models by generalizing a convex program due to Shmyrev and the Eisenberg-Gale program, respectively. -We generalize the Arrow-Hurwicz theorem to the linear case of these two models, hence deriving alternate convex programs. -For the special class of convex programs having convex objective functions and linear constraints, we derive a simple set of rules for constructing the dual program (as simple as obtaining the dual of an LP). Using these rules we show a formal relationship between the two seemingly different convex programs for linear Fisher markets, due to Eisenberg-Gale and Shmyrev; the duals of these are the same, upto a change of variables.
We study anonymous posted price mechanisms for combinatorial auctions in a Bayesian framework. In a posted price mechanism, item prices are posted, then the consumers approach the seller sequentially in an arbitrary order, each purchasing her favorite bundle from among the unsold items at the posted prices. These mechanisms are simple, transparent and trivially dominant strategy incentive compatible (DSIC). We show that when agent preferences are fractionally subadditive (which includes all submodular functions), there always exist prices that, in expectation, obtain at least half of the optimal welfare. Our result is constructive: given black-box access to a combinatorial auction algorithm A, sample access to the prior distribution, and appropriate query access to the sampled valuations, one can compute, in polytime, prices that guarantee at least half of the expected welfare of A. As a corollary, we obtain the first polytime (in n and m) constant-factor DSIC mechanism for Bayesian submodular combinatorial auctions, given access to demand query oracles. Our results also extend to valuations with complements, where the approximation factor degrades linearly with the level of comple
Ad exchanges, i.e., platforms where real-time auctions for ad impressions take place, have developed sophisticated technology and data ecosystems to allow advertisers to target users, yet advertisers may not know which sites their ads appear on, i.e., the ad context. In practice, ad exchanges can require publishers to provide accurate ad placement information to ad buyers prior to submitting their bids, allowing them to adjust their bids for ads at specific domains, subdomains or URLs. However, ad exchanges have historically been reluctant to disclose placement information due to fears that buyers will start buying ads only on the most desirable sites leaving inventory on other sites unsold and lowering average revenue. This paper explores the empirical effect of ad placement disclosure using a unique data set describing a change in context information provided by a major private European ad exchange. Analyzing this as a quasi-experiment using diff-in-diff, we find that average revenue per impression rose when more context information was provided. This shows that ad context information is important to ad buyers and that providing more context information will not lead to deconflat
We study a continuous and infinite time horizon counterpart to the classic prophet inequality, which we term the stationary prophet inequality problem. Here, copies of a good arrive and perish according to Poisson point processes. Buyers arrive similarly and make take-it-or-leave-it offers for unsold items. The objective is to maximize the (infinite) time average revenue of the seller. Our main results are pricing-based policies which (i) achieve a $1/2$-approximation of the optimal offline policy, which is best possible, and (ii) achieve a better than $(1-1/e)$-approximation of the optimal online policy. Result (i) improves upon bounds implied by recent work of Collina et al. (WINE'20), and is the first optimal prophet inequality for a stationary problem. Result (ii) improves upon a $1-1/e$ bound implied by recent work of Aouad and Saritaç (EC'20), and shows that this prevalent bound in online algorithms is not optimal for this problem.
Fashion retailers require accurate demand forecasts for the next season, almost a year in advance, for demand management and supply chain planning purposes. Accurate forecasts are important to ensure retailers' profitability and to reduce environmental damage caused by disposal of unsold inventory. It is challenging because most products are new in a season and have short life cycles, huge sales variations and long lead-times. In this paper, we present a novel product age based forecast model, where product age refers to the number of weeks since its launch, and show that it outperforms existing models. We demonstrate the robust performance of the approach through real world use case of a multinational fashion retailer having over 300 stores, 35k items and around 40 categories. The main contributions of this work include unique and significant feature engineering for product attribute values, accurate demand forecast 6-12 months in advance and extending our approach to recommend product launch time for the next season. We use our fashion assortment optimization model to produce list and quantity of items to be listed in a store for the next season that maximizes total revenue and s
Fashion is a fast-changing industry where designs are refreshed at large scale every season. Moreover, it faces huge challenge of unsold inventory as not all designs appeal to customers. This puts designers under significant pressure. Firstly, they need to create innumerous fresh designs. Secondly, they need to create designs that appeal to customers. Although we see advancements in approaches to help designers analyzing consumers, often such insights are too many. Creating all possible designs with those insights is time consuming. In this paper, we propose a system of AI assistants that assists designers in their design journey. The proposed system assists designers in analyzing different selling/trending attributes of apparels. We propose two design generation assistants namely Apparel-Style-Merge and Apparel-Style-Transfer. Apparel-Style-Merge generates new designs by combining high level components of apparels whereas Apparel-Style-Transfer generates multiple customization of apparels by applying different styles, colors and patterns. We compose a new dataset, named DeepAttributeStyle, with fine-grained annotation of landmarks of different apparel components such as neck, slee
NASA's PACE satellite captured the Black Sea glowing turquoise during its annual phytoplankton bloom。 The vivid color comes from massive numbers of coccolithophores, microscopic organisms whose reflective shells brighten the water enough to be seen from space。 An astronaut aboard the International Space Station also photographed the bloom spreading