AJAyush Jain

Ayush Jain

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ayush Jain has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Data-driven decarbonization framework with machine learning

    by Ayush Jain, Manikandan Padmanaban, Jagabondhu Hazra, Ranjini Guruprasad, Shantanu Godbole, Heriansyah Syam

    Eight major supply chains contribute to more than 50% of the global greenhouse gas emissions (GHG). These supply chains range from raw materials to end-product manufacturing. Hence, it is critical to accurately estimate the carbon footprint of these supply chains, identify GHG hotspots, explain the factors that create the hotspots, and carry out what-if analysis to reduce the carbon footprint of supply chains. Towards this, we propose an enterprise decarbonization accelerator framework with a modular structure that automates carbon footprint estimation, identification of hotspots, explainability, and what-if analysis to recommend measures to reduce the carbon footprint of supply chains. To illustrate the working of the framework, we apply it to the cradle-to-gate extent of the palm oil supply chain of a leading palm oil producer. The framework identified that the farming stage is the hotspot in the considered supply chain. As the next level of analysis, the framework identified the hotspots in the farming stage and provided explainability on factors that created hotspots. We discuss the what-if scenarios and the recommendations generated by the framework to reduce the carbon footprint of the hotspots and the resulting impact on palm oil tree yield.


  • Open Access

    A Framework for Emission Reduction in Scope 3 Climate Actions using Domain-adapted Foundation Model

    by Ayush Jain, Manikandan Padmanaban, Jagabondhu Hazra, Shantanu Godbole, Komminist Weldemariam

    Large enterprises face a crucial imperative to achieve the Sustainable Development Goals (SDGs), especially goal 13, which focuses on combating climate change and its impacts. To mitigate the effects of climate change, reducing enterprise Scope 3 (supply chain emissions) is vital, as it accounts for more than 90% of total emission inventories. However, tracking Scope 3 emissions proves challenging, as data must be collected from thousands of upstream and downstream suppliers. We propose a novel framework that uses domain-adapted NLP foundation model to estimate Scope 3 emissions by leveraging financial transactions as a proxy of embodied emission of purchased goods and services and recommends appropriate climate actions to reduce scope3 emission through counterfactual queries. Our results show that the domain-adapted foundation model outperforms state-of-the-art text mining techniques and performs as well as a subject matter expert (SME). We also show how the proposed framework can identify Scope 3 hotspots and explain the factors that create them. Finally, we carry out what-if analysis to take climate actions that help achieve SDG 13. We present a case study demonstrating how this framework can be used by a real estate enterprise to take Scope 3 climate actions.


  • Open Access

    Towards Context-based Model Selection for Improved Crop Price Forecasting

    by Ayush Jain, Smit Marvaniya, Shantanu Godbole, Vitobha Munigala

    Accuracy of crop price forecasting techniques plays an important role in enabling the supply chain planners and government bodies to take necessary actions by estimating market factors such as demand and supply. In emerging economies such as India, the crop prices at marketplaces are manually entered, which can be prone to human-induced errors like entry of incorrect data or entry of no data for many days. In addition to such human prone errors, the fluctuations in the prices itself make the creation of stable and robust forecasting solution a challenging task. Considering such complexities in crop price forecasting, in this paper, we present techniques to build robust crop price prediction models considering various features such as (i) historical price and market arrival quantity of crops, (ii) historical weather data that influence crop production and transportation, (iii) data quality-related features obtained by performing statistical analysis. Furthermore, we propose a crop-specific context-based model selection strategy using trend analysis to deal with high fluctuations in crop prices. To show the efficacy of the proposed approach, we show experimental results using two different time-series feature representations on two crops - Tomato and Maize for 14 marketplaces in India and demonstrate that the proposed approach provides improved accuracy metrics when compared to standard forecasting techniques.


  • Open Access

    SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

    by Yi Hao, Ayush Jain, Alon Orlitsky, Vaishakh Ravindrakumar

    Sample- and computationally-efficient distribution estimation is a fundamental tenet in statistics and machine learning. We present SURF, an algorithm for approximating distributions by piecewise polynomials. SURF is: simple, replacing prior complex optimization techniques by straight-forward {empirical probability} approximation of each potential polynomial piece {through simple empirical-probability interpolation}, and using plain divide-and-conquer to merge the pieces; universal, as well-known polynomial-approximation results imply that it accurately approximates a large class of common distributions; robust to distribution mis-specification as for any degree $d \le 8$, it estimates any distribution to an $\ell_1$ distance $< 3$ times that of the nearest degree-$d$ piecewise polynomial, improving known factor upper bounds of 3 for single polynomials and 15 for polynomials with arbitrarily many pieces; fast, using optimal sample complexity, running in near sample-linear time, and if given sorted samples it may be parallelized to run in sub-linear time. In experiments, SURF outperforms state-of-the art algorithms.

  • Performance Analysis of Various Generative Adversarial Network using Dog image Dataset

    by Ayush Jain, Ayushi Bansal, Yogesh Kakde

    Generative Adversarial Network is a novel concept for a general purpose solution to Deep Fake Image generation. These networks learn mapping from input image to output image and also assign value in loss function for the same mapping. We demonstrate that this approach is effective to synthesize images from labelled images, and colorizing images, and other tasks. We have investigate performance of three different types of model i.e. simple GAN, DC-GAN, BIG-GAN, which have provided different results with generation of different loss function on the same dataset i.e. Stanford Dogs Dataset. In this paper, we have investigated the performance of models by using inception score and also track the loss function at different stages (epochs).