Objectives: The forecasting of horticulture commodity prices, such as bananas, has wide-ranging impacts on farmers, traders and end-users. The considerable volatility in horticultural commodities pricing estimates has allowed farmers to exploit various local marketplaces for profitable sales of their farm produce. Despite the demonstrated efficacy of machine learning models as a suitable substitute for conventional statistical approaches, their application for price forecasting in the context of Indian horticulture remains an area of contention. Past attempts to forecast agricultural commodity prices have relied on a wide variety of statistical models, each of which comes with its own set of limitations. Methods: Although machine learning models have emerged as formidable alternatives to more conventional statistical methods, there is still reluctance to use them for the purpose of predicting prices in India. In the present investigation, we have analysed and compared the efficacy of a variety of statistical and machine learning models in order to get accurate price forecast. Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average model (SARIMA), Autoregressive Conditional Heteroscedasticity model (ARCH), Generalized Autoregressive Conditional Heteroscedasticity model (GARCH), Artificial Neural Network (ANN) and Recurrent Neural Network (RNN) were fitted to generate reliable predictions of prices of banana in Gujarat, India from January 2009 to December 2019. Results: Empirical comparisons have been made between the predictive accuracy of different machine learning (ML) models and the typical stochastic model and it is observed that ML approaches, especially RNN, surpassed all other models in the majority of situations. Mean Absolute Percent Error (MAPE), Root Mean Square Error (RMSE), symmetric mean absolute percentage error (SMAPE), mean absolute scaled error (MASE) and mean directional accuracy (MDA) are used to illustrate the superiority of the models and RNN resulted least in terms of all error accuracy measures. Conclusions: RNN outperforms other models in this study for predicting accurate prices when compared to various statistical and machine learning techniques. The accuracy of other methodologies like ARIMA, SARIMA, ARCH GARCH, and ANN falls short of expectations.

The comparative economics of banana cultivation under drip and conventional irrigation methods was studied by collecting data from 60 drip farms and 60 non-drip farms of Anand district during 2009–10. Though the investment on drip irrigation system for banana crop was expensive ( 84115/ha), the total cost of cultivation in drip farms ( 150098/ha) was slightly less than that in non-drip farms ( 151735/ha). The yield (13.94 per cent) and net profit (52.76 per cent) of banana in drip farms were higher as compared to non-drip farms. Input-Output ratio over cost-c₂ under drip and flood method of irrigation was 2.10 and 1.71, respectively. The Cobb-Douglas production function was employed to establish the input-output relationship. The sum of regression co-efficient (Σbi's) was 1.072 and 1.109 for non-drip and drip banana farms, respectively indicating increasing return to scale. MVP/FC ratios were also worked out to examine the resource use efficiency more reliably. It was found that the resources viz, plantlets (tissue culture), irrigation and area were underutilized in drip farms indicating these inputs were not optimum in context to other inputs in order to get maximum profit and therefore, there is yet some scope to increase productivity in the study area of drip farms of banana.

Despite scientific proof of the benefits and effects of fish consumption on human health, most Indians consume less than the recommended dietary amounts. The current study attempted to assess the knowledge gap of fish eaters regarding the health and nutritional benefits, along with identifying the factors that directly and indirectly influence the knowledge level of fish consumers. The fish eaters were surveyed during the F.Y. 2021–2022 with representative samples of 934 fish consumers from across ten districts of the Gujarat state in western India. Fish consumers were found to have insufficient knowledge about health and nutritional benefits, which stalled the growth of fish consumption in the region. The significant factors influencing the knowledge level of fish consumers were education qualification, fish quality evaluation criteria, number of children in a family, years of fish consumption and family size. The consumers were found to place greater emphasis on the fish quality evaluation parameters such as smell, appearance, nutritional value, product price and freshness. The study’s outcomes suggested that mass awareness programs should be planned to achieve higher levels of fish consumption in the region and the country.

Background: This paper presents the economic analysis of potato cultivation in middle Gujarat. The area under total vegetable and production of vegetables in the state has increased over the years. The study focuses on production and marketing of potato in middle Gujarat. Methods: Primary data were collected using pre-tested schedule. The cost of production was calculated using cost concept and marketing efficiency was calculated using Acharya’s formula. Result: The study found that the cost C2 was ₹ 208587.5 per hectare for potato cultivation. Yield of potato was found to be 242.5 quintal per hectare, while gross income was ₹ 247370.4 per hectare. The net return was observed to be at ₹ 38782.9 per ha for potato cultivation. Benefit cost ratio over cost C2 was observed to be at 1.19. There were two marketing channels found in potato in study area. The market efficiency was found higher in channel I. Unavailability of labour, long distance of input market and increasing prices of inputs were the major production constraints, while low price received by farmer, delayed in payment and higher cost of transportation were the major marketing constraint found in study area.