Design and Implementation of a Three-Layer Backpropagation Neural Network for Multi-Output Regression in Citizen-Science Impact Assessment

Measuring the impact of citizen science projects is hard because inputs are heterogeneous, mostly categorical, and sparse. We present Alquimics, a compact supervised neural network trained on one hot project descriptors to predict impact across five domains (Environment, Economy, Governance, Science, and Society). Each project is encoded as a binary vector of length 4,460 (223 questions × 20 options, flattened). The network employs a 4,460–42–5 topology with logistic activations throughout; labels consist of five continuous targets in [0, 1] obtained by scaling expert domain scores in [1, 42]. We implement L2 regularised training in Octave using fmincg with MaxIter = 10 and lambda = 0.07. We document the entire data pipeline, objective, and implementation, provide a minimal reproducible script, and discuss limitations arising from the small dataset (n = 9 projects). This establishes a transparent baseline that complements rule based scoring and can be expanded as more labelled projects become available.